Academic literature on the topic 'Expressivité vocale'

This study is a third-year (34 months) follow-up investigation of the socioemotional behaviours of preterm and fullterm children previously seen at four points in time during the first two years of life. A total of 42 mother/ child pairs were seen for videotaped mother/child and child/peer play sessions. The tapes were coded on a second-to-second basis using Izard's MAX facial affect coding system and a vocal affect coding system. Data analysis focused on the contribution of the individual difference variables of gender, birth status, attachment classification, and maternal contingency behaviour, to children's expressive development. Expressive patterns in the third year were also compared with those obtained during the children's second year. Results indicated that contrary to developmental theory, facial expressivity does not decrease, at least during this developmental period, and moreover, that vocal affective expression increases. It is suggested that what children learn in development, is greater flexibility in the use of different systems to communicate affect, and greater facility in modulating expressivity according to context. Birth status was found to continue to affect the nature of affective development into the third year; preterm children were less vocally expressive than their fullterm counterparts, and preterm females showed greater facial negativity. Few other gender differences in expressivity were apparent, although mothers treated their children differentially. Moderate maternal contingency in infancy was related to greater vocal affectivity in children. Insecure attachment was associated with a degree of apparent tension and affective disharmony.

Abstract Limited expressivity of emotion is one of the most common symptoms of major depression, particularly in older adults. Although assessing facial and vocal expressivity is very important for accurate clinical evaluation of geriatric depression, research has rarely examined older adults via telehealth technology. This study aims to quantify facial and vocal expressivity via a multimodal affective system with deep learning. A total of 19 Korean adults aged over 65 years with severe depressive symptoms participated in this research. Using smartphone video recording, 1,429 facial and vocal data were collected between July and December 2020. Recorded videos were transmitted automatically to the cloud system. Basic facial movements were extracted using combined video frames and mel spectrogram images. Compared to the AI hub of Korean images from big data, mood status was classified into seven categories (anger, disgust, fear, happiness, neutrality, sadness, and surprise). Frequencies of each mood were coded into continuous variables for each participant in each recording. When comparing video and text prediction to determine “true labels,” the overall accuracy was 0.69, with F1 scores ranging from 0.57 to 0.79. In addition, the most common emotions were angry, happy, neutral, sad, and surprised. This study suggests that smartphone-recorded video could function as a useful tool for quantifying mood expressivity. This study established a preliminary method of affective assessment for older adults for telecare use based on socially assistive technology at a distance from the clinic.

Background Machine learning–based facial and vocal measurements have demonstrated relationships with schizophrenia diagnosis and severity. Demonstrating utility and validity of remote and automated assessments conducted outside of controlled experimental or clinical settings can facilitate scaling such measurement tools to aid in risk assessment and tracking of treatment response in populations that are difficult to engage. Objective This study aimed to determine the accuracy of machine learning–based facial and vocal measurements acquired through automated assessments conducted remotely through smartphones. Methods Measurements of facial and vocal characteristics including facial expressivity, vocal acoustics, and speech prevalence were assessed in 20 patients with schizophrenia over the course of 2 weeks in response to two classes of prompts previously utilized in experimental laboratory assessments: evoked prompts, where subjects are guided to produce specific facial expressions and speech; and spontaneous prompts, where subjects are presented stimuli in the form of emotionally evocative imagery and asked to freely respond. Facial and vocal measurements were assessed in relation to schizophrenia symptom severity using the Positive and Negative Syndrome Scale. Results Vocal markers including speech prevalence, vocal jitter, fundamental frequency, and vocal intensity demonstrated specificity as markers of negative symptom severity, while measurement of facial expressivity demonstrated itself as a robust marker of overall schizophrenia symptom severity. Conclusions Established facial and vocal measurements, collected remotely in schizophrenia patients via smartphones in response to automated task prompts, demonstrated accuracy as markers of schizophrenia symptom severity. Clinical implications are discussed.

In the opera Sing the Body Electric! A Corporatorio, artists from the disciplines of opera, dance and the development of new musical instruments collaborated to create an onstage fusion of different technologies and artistic practices that connected performer, scenography and instrument. Gestures and movements of singers were captured by custom-built technologies. The singers also used custom-built technologies for transforming their vocal qualities and for creating synthesized accompaniment in real time. In this way the singers’ bodily musical processes further extended their vocal performances, rooted in operatic praxis, allowing for heightened expressivity and emergent scenic subjects.

<p class="abstract">Thymomas are rare tumors of the anterior mediastinum that may be benign or malignant. Thymomas are frequently associated with neuromuscular disorders like myasthenia gravis. Multiple cranial nerves are involved which may affect speech of the patients. Flaccid dysarthria is one of the common motor speech disorders associated with thymoma. Other characteristics may include decrease of intelligibility, reduced vocal stamina, reduction of emotional expressivity etc. The present case study illustrates changes in speech characteristics in a 35 year old male patient with thymoma associated with myasthenia gravis. Detailed speech assessment was done which revealed deviant speech patterns like vocal tremors, decreased loudness, hypernasality etc. The aim of the study was to document speech characteristics in a known case of thymoma associated with myasthenia gravis.</p>

The article examines the genres of the vocal and the choral symphony in connection with the author’s vocal symphony Finland for soprano, tenor and orchestra set to Evgeny Baratynsky’s poem with the same title. It also discusses the issue of expression of the literary text in vocal music, as viewed by a number of influential 19th and 20th century composers, music theorists and artists. Among the greatest examples of the vocal symphony are Gustav Mahler’s Das Lied von der Erde and Alexander von Zemlinsky’s Lyrische Symphonie. These works combine in an organic way the features of the symphony and the song cycle. The genre of the choral symphony started with Beethoven’s Ninth Symphony and includes such works as Mendelssohn’s Second Symphony, Scriabin’s First Symphony and Mahler’s Second, Third and Eighth Symphonies. Both genres exemplify composers’ attempts to combine the most substantial genre of instrumental music embodying the composers’ philosophical worldviews with that of vocal music, which expresses the emotional content of the literary texts set to music. The issue of expressivity in music is further elaborated in examinations of various composers’ approaches to it. Wagner claimed that the purpose of music was to express the composers’ emotional experience and especially the literary texts set to music. Stravinsky expressed the view that music in its very essence is not meant to express emotions. He called for an emotionally detached approach to music and especially to text settings in vocal music. Schoenberg pointed towards a more introversive and abstract approach to musical expression and text setting in vocal music, renouncing outward depiction for the sake of inner expression. Similar attitudes to this position were held by painter Wassily Kandinsky and music theorist Theodor Adorno. The author views Schoenberg’s approach to be the most viable for 20th and early 21st century music.

The article discusses the relationships between musical performance, theatrical space and gesturality in Christoph Marthaler’s operatic productions. The stage design, the types of actor’s physical and vocal expressivity in “Le Nozze di Figaro”, “La Grande Duchesse de Gérolstein”, “Kát’a Kabanová”, “Věc Makropulos”, “Les Contes d’Hoffmann” and “Tristan und Isolde” are studied. Gesture, vocalisation and text in Marthaler’s productions are discussed and interpreted by considering the mismatching of dance and musical rhythm, the contrast of academical and non-academical singing manners or soundless articulation, as well as emphasizing the visual side of musical performance. Ensemble music-making and figurative gestures are the metaphors of power relations, total control and the collapse of social structures. It is concluded that the ways of vocalization and the types of gestures embody the system of power. The society in Marthaler’s operatic stage productions appears as an ensemble of the discursive practices.

The article presents the results of the cyclical organization of Pierre Boulez’s Le Marteau sans maître in the aspect of combining the principles of linear and non-linear organization. The composer created a work of a probabilistic type, in which dispersed and localized sub-cycles coexist with each other. Their core is formed by the vocal movements in which René Char’s poems are interpreted. The number of compositional units in these structural-thematic groups coincides with the quantitative factor of the segments of the composition’s main series. The embedding of sub-cycles homogenous in their content into a linear set is analogous to the procedure of interpolation. In the dispersed sub-cycles Char’s title poem stipulates the system of expressive means which is replicated in all the movements at various levels of fullness, but always in recognizable ways. In the localized structural-thematic groups the wholeness is formed in the process of ascertainment of the substantial images and the common elements of musical expressivity in the movements pertaining to various sub-cycles. Here the vocal movement becomes the “point of convergence” which brings to light the coincidences and activates the additional semantic overtones present in the poem. In his Le Marteau sans maîtreBoulez demonstrated the possibilities of compositional variability in the conditions of the system of cycles created by them presuming the simultaneous activity of the linear and non-linear organization with various types of connection.

Objectives: Mindfulness has been explored in the clinical and educational fields but has rarely been studied in the music domain. This study investigated the effects of teaching eight-week Mindfulness for Singers courses on vocalists’ music education and performance. Methods: A mixed methods approach was utilized, which included controlled and randomized controlled trials using standardized and novel mindfulness measures pre- and post-intervention, interviews post-intervention and three months later, concurrent diaries, and a blinded teacher study. Participants included singing students (total n=52) and their teachers ( n=11) from a university and a music college over a period of two years. Results: Levels of mindfulness increased over the intervention for experimental participants in comparison to controls. Considering their total student cohort, teachers identified 61% of eligible mindfulness singing participants as having completed the mindfulness intervention. Experimental participants reported that learning mindfulness had positive effects in lessons, solo and group instrumental practices, and when performing on stage. They described more focus and attention, positive effects of increased body awareness on singing technique, enhanced socio-collaborative relationships, reductions in performance anxiety, and beneficial effects whilst performing, such as more expressivity and enjoyment. Conclusions: Learning mindfulness had positive holistic effects on vocal students and was well received by their mindfulness-naïve singing teachers. Findings suggest that it would be highly beneficial for mindfulness to be made available in music conservatoires and university music departments alongside singing lessons for singers to enhance their present experience as vocal students and their futures as performers and teachers.

La synthèse de parole expressive constitue aujourd'hui un nouveau défi . Un moyen direct de rendre la synthèse expressive consiste à la contrôler en temps réel par les gestes d'un opérateur. Notre recherche s'est donc déroulée selon deux axes : d'une part la modi fication prosodique (hauteur et durée) de la parole enregistrée, et d'autre part la synthèse de voyelles à partir d'un modèle de source glottique. Concernant la modifi cation prosodique, nous avons implémenté un algorithme temps réel permettant la modifi cation conjointe de la hauteur et de la durée d'une phrase enregistrée. Grâce à cet outil, nous avons mené des expériences visant à valider la possibilité de modi fier la prosodie grâce au geste. Nos expériences ont montré la possibilité de reproduire avec précision une intonation donnée grâce au geste manuel. Le second axe de notre recherche s'est focalisé sur la réalisation d'un synthétiseur de voyelles, dont on peut modi fier la qualité vocale. La première étape a consisté à implémenter une version temps réel de la synthèse de l'onde de débit glottique, ainsi que des apériodicités de la source vocale. Nous pouvons ainsi contrôler la fréquence fondamentale, l'eff ort vocal, la tension, le souffle, les apériodicités structurelles et les di fférents mécanismes laryngés. Une attention particulière a été apportée à la réalisation du phonétogramme, ainsi qu'aux correspondances perceptives entre les paramètres du modèle et les dimensions vocales. Notre étude permet d'envisager à terme la modifi cation conjointe, interactive, des composantes prosodiques et de qualité vocale.

L’enjeu de cette thèse est d’étudier la chanson non dans sa dialectique parole/musique, mais par la saisie d’une troisième entité : l’interprétation vocale. Il s’agit à la fois d’en faire émerger l’importance fondamentale et la richesse et de lui conférer sa légitimité d’objet d’étude par la mise en place d’un protocole méthodologique et lexical spécifique qui en autorise l’analyse – au même titre que la composition – malgré son caractère mouvant et réputé réfractaire à la théorisation. Abordée comme objet complexe (selon la terminologie d’Edgar Morin), elle est soumise au feu croisé des disciplines (musicologie, linguistique, rhétorique, acoustique) pour pousser autant qu’il est possible son objectivation. Sous l’égide de la musicologie, l’utilisation d’outils informatiques permet d’établir une complémentarité entre les perspectives des sciences humaines et des sciences exactes, de capter et d’analyser les spécificités interprétatives, aussi bien dans leurs caractères dominants qu’agogiques, leurs rapports à la partition, leur complexité combinatoire au sein des méta-paramètres (timbre, rythme, phrasé) et les tensions dialogiques qui les parcourent (variation/répétition, mélodicité/insertion du bruit, chanté/parlé). Le large corpus de chanteurs d’expression française (du style Rive gauche à la Nouvelle chanson française) permet d’appréhender, au travers d’analyses d’enregistrements en studio ou en concert, la spécificité irréductible de chacun, émanation d’un corps unique, mais aussi de grands réseaux tendanciels de parentés stylistiques. Mise en avant par la perspective sémiologique, autour des notions de stratégie et de visées interprétatives, de rhétorique vocale, de suscitation du pathos et d’expression de l’ethos, se fait jour une typologie des styles interprétatifs, ouverte sur la prise en compte de l’originalité intrinsèque de chaque interprète et sur l’intégration des évolutions génériques ultérieures
The present thesis focuses on the study of the song not in its word and music dialectic but through the acquisition of a third entity : the vocal rendition. The point is to reveal its critical importance and richness and make it legitimate as a subject of study as the result of the implementation of a specific methodological and lexical protocol that allows the analysis – as with the composition – although its changeable nature is not conducive to theorizing. Considered as a complex object (according to Edgar Morin’s terminology), vocal rendition is submitted to the crossfire of various disciplines (musicology, linguistics, rhetoric, acoustics) in order to favour as far as it is possible its objectivization. Within the framework of musicology, the use of computer tools makes it possible to establish a complementarity between the perspectives of social sciences and exact sciences, to catch and analyse the peculiarities of the performances both in their dominant or agogic characters, their connexions to the score, their combinatorial complexity within the meta-parameters (timbre, rhythm, phrasing), as well as the dialogical tensions which run through them (variation and repetition, melodicity and noise integration, singing and speaking parts). Thanks to the existence of a large body of French-speaking singers (from Rive Gauche style to Nouvelle chanson française) it is possible by studying studio and concert recordings to grasp the irreducible specificity of everyone (what is issued from a unique body) as well as the great underlying networks of stylistic relationships. Disclosed by the semeiological perspective, around the notions of strategy and performance designs, vocal rhetoric, the way to induce pathos and to express ethos, there emerges a typology of performing styles that is open to considering the intrinsic originality of each performer and integrating further generic developments

Cette thèse s'inscrit dans le cadre de la synthèse de parole à partir du texte. Elle traite plus précisément du procédé de création de voix en synthèse par sélection d'unités. L'état de l'art repose pour cela sur l'enregistrement d'un locuteur pendant une à deux semaines, suivant un script de lecture de plusieurs dizaines de milliers de mots. Les 5 à 10 heures de parole collectées sont généralement révisées par des opérateurs humains, pour en vérifier la segmentation phonétique et ainsi améliorer la qualité finale de la voix de synthèse.La lourdeur générale de ce procédé freine considérablement la diversification des voix de synthèse ; aussi en proposons-nous ici une rationalisation. Nous introduisons une nouvelle unité, appelée "sandwich vocalique", pour l'optimisation de la couverture des scripts de lecture. Sur le plan phonétique, cette unité offre une meilleure prise en compte des limites segmentales de la synthèse par sélection que les unités traditionnelles (diphones, triphones, syllabes, mots, etc.). Sur le plan linguistique, un nouvel enrichissement contextuel nous permet de mieux focaliser la couverture, sans négliger les aspects prosodiques. Nous proposons des moyens d'accroître le contrôle sur les phrases du script lecture, tant dans leur longueur que dans leur pertinence phonétique et prosodique, afin de mieux anticiper le contenu du corpus de parole final et de rendre automatisable la tâche de segmentation. Nous introduisons également une alternative à la stratégie classique de condensation de corpus en mettant au point un algorithme semi-automatique de création de phrases, grâce auquel nous accroissons de 30 à 40% la densité linguistique du script de lecture.Ces nouveaux outils nous permettent d'établir un procédé très efficace de création de voix de synthèse, procédé que nous validons à travers la création et l'évaluation subjective de nombreuses voix. Des scores perceptifs comparables à l'approche traditionnelle sont ainsi atteints dès 40 minutes de parole (une demi-journée d'enregistrement) et sans post-traitement manuel. Enfin, nous mettons à profit ce résultat pour enrichir nos voix de synthèse de diverses composantes expressives, multi-expressives et paralinguistiques.

Cette thèse s'inscrit dans le cadre de la synthèse de parole à partir du texte. Elle traite plus précisément du procédé de création de voix en synthèse par sélection d'unités. L'état de l'art repose pour cela sur l'enregistrement d'un locuteur pendant une à deux semaines, suivant un script de lecture de plusieurs dizaines de milliers de mots. Les 5 à 10 heures de parole collectées sont généralement révisées par des opérateurs humains, pour en vérifier la segmentation phonétique et ainsi améliorer la qualité finale de la voix de synthèse.La lourdeur générale de ce procédé freine considérablement la diversification des voix de synthèse ; aussi en proposons-nous ici une rationalisation. Nous introduisons une nouvelle unité, appelée "sandwich vocalique", pour l'optimisation de la couverture des scripts de lecture. Sur le plan phonétique, cette unité offre une meilleure prise en compte des limites segmentales de la synthèse par sélection que les unités traditionnelles (diphones, triphones, syllabes, mots, etc.). Sur le plan linguistique, un nouvel enrichissement contextuel nous permet de mieux focaliser la couverture, sans négliger les aspects prosodiques. Nous proposons des moyens d'accroître le contrôle sur les phrases du script lecture, tant dans leur longueur que dans leur pertinence phonétique et prosodique, afin de mieux anticiper le contenu du corpus de parole final et de rendre automatisable la tâche de segmentation. Nous introduisons également une alternative à la stratégie classique de condensation de corpus en mettant au point un algorithme semi-automatique de création de phrases, grâce auquel nous accroissons de 30 à 40% la densité linguistique du script de lecture.Ces nouveaux outils nous permettent d'établir un procédé très efficace de création de voix de synthèse, procédé que nous validons à travers la création et l'évaluation subjective de nombreuses voix. Des scores perceptifs comparables à l'approche traditionnelle sont ainsi atteints dès 40 minutes de parole (une demi-journée d'enregistrement) et sans post-traitement manuel. Enfin, nous mettons à profit ce résultat pour enrichir nos voix de synthèse de diverses composantes expressives, multi-expressives et paralinguistiques
This work falls within the scope of text-to-speech (TTS) technology. More precisely, focus is on the voice creation process for unit-selection synthesis. In a standard approach, a textual script of several thousands of words is read by a speaker in order to generate approximately 5 to 10 hours of useable speech. The recording time is spread out over one or two weeks and is followed by the considerable task of manually revising the phonetic segmentation for all of the speech.Such a costly and time-consuming process presents a major obstacle to diversifying synthesized voices. In order to increase efficiency in this process, we introduce a new unit, called a "vocalic sandwich", to optimize coverage of the recording texts. Phonetically, this unit better addresses the segmental limitations of unit-selection TTS than state-of-the-art units (diphones, triphones, syllables, words...). Linguistically, a new set of contextual symbols focuses the coverage, allowing for more control and consideration of prosody. Practically, in order to automate the segmentation process, better anticipation of the phonetic and prosodic content desired in the final database is required. This is achieved here by increasing the readability and consistency of each sentence included in the script. As a side, these properties also help to facilitate the reading stage. Furthermore, as an alternative to the classic corpus condensation, a semi-automatic sentence building algorithm is developed in this work wherein sentences are built rather than selected from a reference corpus. Ultimately, the sentence building provides access to much denser scripts, specifically allowing for increases in density of between 30 and 40%.In incorporating these new approaches and tools, the voice creation process is made very efficient, as is validated in this work through the preparation and evaluation of numerous synthesized voices. Perceptive scores that are comparable to the traditional process are achieved with 40 minutes of speech (half-day recording) and without any manual post-processing. Finally, we take advantage of these results in order to enhance our synthesized voices with various expressive, multi-expressive and paralinguistic features

S’écouter, se répondre, faire se coïncider, se coordonner, s’accorder, se suivre, s’adapter, être à l’unisson, se synchroniser, s’aligner... Le riche vocabulaire dédié à la mise en correspondance dans le temps des activités humaines montre l’importance que revêt leur organisation temporelle. La communication humaine, multi-modale par nature, est pleinement concernée par cette problématique puisqu’il existe un écart sémantique entre les locutions orales et leurs séquences symboliques : comment bien interpréter un message écrit sans l’intonation vocale ? quel style performatif au delà d’une partition musicale figée ? Cette thèse se propose de révéler et expliquer les complexes relations entre les domaines audio et symbolique afin de réduire cet écart grâce à l’étude fine de l’inhérente temporalité contenue dans les enregistrements vocaux. Au coeur de cet objectif, se trouve la tâche d’alignement de voix qui vise à déterminer l’occurrence temporelle de symboles supposés présents dans un signal vocal. Ces travaux s’intéressent tout particulièrement au développement d’un modèle acoustique, ADAGIO, capable d’estimer de tels liens temps-symboles. Les récents progrès en apprentissage profond amènent à implémenter ADAGIO sous la forme d’un réseau de neurones profond dans un puissant formalisme générique : la “Classification Temporelle Connectioniste” (CTC). Cependant, la grande flexibilité offerte par la CTC est mise en défaut par son absence intrinsèque de garanties de prédictions temporellement précises. Les contributions clefs de cette recherche visent à renforcer la CTC par des contraintes temporelles supplémentaires pour améliorer la qualité des alignements déduits. Pour cela, trois tâches annexes de (1) reconstruction du contenu spectral, (2) propagation de la structure audio, et (3) monotonie guidée sont introduites et induisent un impact positif sur l’alignement entre voix, textes, et notes. Dès lors, ADAGIO contribue à de nombreuses applications pratiques au travers de collaborations telles que la synthèse vocale concaténative ou l’étude des stratégies de production expressives en jeu tant pour les attitudes sociales dans la parole que pour le style de chant dans des performances musicales
To listen, to respond, to make coincide, to coordinate, to adjust, to follow, to adapt, to be in unison, to synchronize, to align... The rich vocabulary dedicated to the correspondence of human activities shows the importance of their temporal organization. Human communication, multi-modal by nature, is fully concerned by this problematic since there exists a semantic gap between oral locutions and their symbolic sequences: how to interpret a written message without the vocal intonation? what performative style beyond a fixed musical score? This thesis proposes to uncover the complex underlying relationships between the audio and symbolic domains in order to reduce this gap through the fine study of the inherent temporality contained in voice recordings. The voice alignment task lies at the core of this objective, as it aims to determine the temporal occurrence of symbols that are assumed to be present in a voice signal. This work notably focuses on the development of an acoustic model, ADAGIO, capable of estimating such time-symbol links. Recent progress in deep learning have led to implement ADAGIO as a deep neural network in a powerful generic formalism: the “Connectionist Temporal Classification” (CTC). However, the great flexibility offered by CTC is undermined by its intrinsic lack of guarantees for temporally accurate predictions. Therefore, the key contributions of this research consist in reinforcing CTC with additional temporal constraints to improve the quality of the inferred alignments. To do so, three ancillary tasks of (1) spectral content reconstruction; (2) audio structure propagation; and (3) guided monotony are introduced and induce a positive impact on the alignment between voices, texts, and notes. Then, ADAGIO contributes to many practical applications via collaborations such as concatenative speech synthesis or the study of expressive production strategies at play for both social attitudes in speech and singing style in musical performances

Aquesta tesi s'ha dut a terme dins del Grup en de Tecnologies Mèdia (GTM) de l'Escola d'Enginyeria i Arquitectura la Salle. El grup te una llarga trajectòria dins del cap de la síntesi de veu i fins i tot disposa d'un sistema propi de síntesi per concatenació d'unitats (US-TTS) que permet sintetitzar diferents estils expressius usant múltiples corpus. De forma que per a realitzar una síntesi agressiva, el sistema usa el corpus de l'estil agressiu, i per a realitzar una síntesi sensual, usa el corpus de l'estil corresponent. Aquesta tesi pretén proposar modificacions del esquema del US-TTS que permetin millorar la flexibilitat del sistema per sintetitzar múltiples expressivitats usant només un únic corpus d'estil neutre. L'enfoc seguit en aquesta tesi es basa en l'ús de tècniques de processament digital del senyal (DSP) per aplicar modificacions de senyal a la veu sintetitzada per tal que aquesta expressi l'estil de parla desitjat. Per tal de dur a terme aquestes modificacions de senyal s'han usat els models harmònic més soroll per la seva flexibilitat a l'hora de realitzar modificacions de senyal. La qualitat de la veu (VoQ) juga un paper important en els diferents estils expressius. És per això que es va estudiar la síntesi de diferents emocions mitjançant la modificació de paràmetres de VoQ de baix nivell. D'aquest estudi es van identificar un conjunt de limitacions que van donar lloc als objectius d'aquesta tesi, entre ells el trobar un paràmetre amb gran impacte sobre els estils expressius. Per aquest fet l'esforç vocal (VE) es va escollir per el seu paper important en la parla expressiva. Primer es va estudiar la possibilitat de transferir l'VE entre dues realitzacions amb diferent VE de la mateixa paraula basant-se en la tècnica de predicció lineal adaptativa del filtre de pre-èmfasi (APLP). La proposta va permetre transferir l'VE correctament però presentava limitacions per a poder generar nivells intermitjos d'VE. Amb la finalitat de millorar la flexibilitat i control de l'VE expressat a la veu sintetitzada, es va proposar un nou model d'VE basat en polinomis lineals. Aquesta proposta va permetre transferir l'VE entre dues paraules qualsevols i sintetitzar nous nivells d'VE diferents dels disponibles al corpus. Aquesta flexibilitat esta alineada amb l'objectiu general d'aquesta tesi, permetre als sistemes US-TTS sintetitzar diferents estils expressius a partir d'un únic corpus d'estil neutre. La proposta realitzada també inclou un paràmetre que permet controlar fàcilment el nivell d'VE sintetitzat. Això obre moltes possibilitats per controlar fàcilment el procés de síntesi tal i com es va fer al projecte CreaVeu usant interfícies gràfiques simples i intuïtives, també realitzat dins del grup GTM. Aquesta memòria conclou presentant el treball realitzat en aquesta tesi i amb una proposta de modificació de l'esquema d'un sistema US-TTS per incloure els blocs de DSP desenvolupats en aquesta tesi que permetin al sistema sintetitzar múltiple nivells d'VE a partir d'un corpus d'estil neutre. Això obre moltes possibilitats per generar interfícies d'usuari que permetin controlar fàcilment el procés de síntesi, tal i com es va fer al projecte CreaVeu, també realitzat dins del grup GTM. Aquesta memòria conclou presentant el treball realitzat en aquesta tesi i amb una proposta de modificació de l'esquema del sistema US-TTS per incloure els blocs de DSP desenvolupats en aquesta tesi que permetin al sistema sintetitzar múltiple nivells d'VE a partir d'un corpus d'estil neutre.
Esta tesis se llevó a cabo en el Grup en Tecnologies Mèdia de la Escuela de Ingeniería y Arquitectura la Salle. El grupo lleva una larga trayectoria dentro del campo de la síntesis de voz y cuenta con su propio sistema de síntesis por concatenación de unidades (US-TTS). El sistema permite sintetizar múltiples estilos expresivos mediante el uso de corpus específicos para cada estilo expresivo. De este modo, para realizar una síntesis agresiva, el sistema usa el corpus de este estilo, y para un estilo sensual, usa otro corpus específico para ese estilo. La presente tesis aborda el problema con un enfoque distinto proponiendo cambios en el esquema del sistema con el fin de mejorar la flexibilidad para sintetizar múltiples estilos expresivos a partir de un único corpus de estilo de habla neutro. El planteamiento seguido en esta tesis esta basado en el uso de técnicas de procesamiento de señales (DSP) para llevar a cabo modificaciones del señal de voz para que este exprese el estilo de habla deseado. Para llevar acabo las modificaciones de la señal de voz se han usado los modelos harmónico más ruido (HNM) por su flexibilidad para efectuar modificaciones de señales. La cualidad de la voz (VoQ) juega un papel importante en diferentes estilos expresivos. Por ello se exploró la síntesis expresiva basada en modificaciones de parámetros de bajo nivel de la VoQ. Durante este estudio se detectaron diferentes problemas que dieron pié a los objetivos planteados en esta tesis, entre ellos el encontrar un único parámetro con fuerte influencia en la expresividad. El parámetro seleccionado fue el esfuerzo vocal (VE) por su importante papel a la hora de expresar diferentes emociones. Las primeras pruebas se realizaron con el fin de transferir el VE entre dos realizaciones con diferente grado de VE de la misma palabra usando una metodología basada en un proceso filtrado de pre-émfasis adaptativo con coeficientes de predicción lineales (APLP). Esta primera aproximación logró transferir el nivel de VE entre dos realizaciones de la misma palabra, sin embargo el proceso presentaba limitaciones para generar niveles de esfuerzo vocal intermedios. A fin de mejorar la flexibilidad y el control del sistema para expresar diferentes niveles de VE, se planteó un nuevo modelo de VE basado en polinomios lineales. Este modelo permitió transferir el VE entre dos palabras diferentes e incluso generar nuevos niveles no presentes en el corpus usado para la síntesis. Esta flexibilidad está alineada con el objetivo general de esta tesis de permitir a un sistema US-TTS expresar múltiples estilos de habla expresivos a partir de un único corpus de estilo neutro. Además, la metodología propuesta incorpora un parámetro que permite de forma sencilla controlar el nivel de VE expresado en la voz sintetizada. Esto abre la posibilidad de controlar fácilmente el proceso de síntesis tal y como se hizo en el proyecto CreaVeu usando interfaces simples e intuitivas, también realizado dentro del grupo GTM. Esta memoria concluye con una revisión del trabajo realizado en esta tesis y con una propuesta de modificación de un esquema de US-TTS para expresar diferentes niveles de VE a partir de un único corpus neutro.
This thesis was conducted in the Grup en Tecnologies M`edia (GTM) from Escola d’Enginyeria i Arquitectura la Salle. The group has a long trajectory in the speech synthesis field and has developed their own Unit-Selection Text-To-Speech (US-TTS) which is able to convey multiple expressive styles using multiple expressive corpora, one for each expressive style. Thus, in order to convey aggressive speech, the US-TTS uses an aggressive corpus, whereas for a sensual speech style, the system uses a sensual corpus. Unlike that approach, this dissertation aims to present a new schema for enhancing the flexibility of the US-TTS system for performing multiple expressive styles using a single neutral corpus. The approach followed in this dissertation is based on applying Digital Signal Processing (DSP) techniques for carrying out speech modifications in order to synthesize the desired expressive style. For conducting the speech modifications the Harmonics plus Noise Model (HNM) was chosen for its flexibility in conducting signal modifications. Voice Quality (VoQ) has been proven to play an important role in different expressive styles. Thus, low-level VoQ acoustic parameters were explored for conveying multiple emotions. This raised several problems setting new objectives for the rest of the thesis, among them finding a single parameter with strong impact on the expressive style conveyed. Vocal Effort (VE) was selected for conducting expressive speech style modifications due to its salient role in expressive speech. The first approach working with VE was based on transferring VE between two parallel utterances based on the Adaptive Pre-emphasis Linear Prediction (APLP) technique. This approach allowed transferring VE but the model presented certain restrictions regarding its flexibility for generating new intermediate VE levels. Aiming to improve the flexibility and control of the conveyed VE, a new approach using polynomial model for modelling VE was presented. This model not only allowed transferring VE levels between two different utterances, but also allowed to generate other VE levels than those present in the speech corpus. This is aligned with the general goal of this thesis, allowing US-TTS systems to convey multiple expressive styles with a single neutral corpus. Moreover, the proposed methodology introduces a parameter for controlling the degree of VE in the synthesized speech signal. This opens new possibilities for controlling the synthesis process such as the one in the CreaVeu project using a simple and intuitive graphical interfaces, also conducted in the GTM group. The dissertation concludes with a review of the conducted work and a proposal for schema modifications within a US-TTS system for introducing the VE modification blocks designed in this dissertation.

The beginning of the 20th century saw the rise of modernist aesthetics which moulded modern performance practice. This change caused a steadfast distancing from the expressive practices of the late 19th century which were part of a continuum of practice going back to the 18th century or earlier. Recordings of singers, who in some cases were trained in the 1830s and 1840s, provide first-hand evidence of these late 19th-century practices and give insight into their embodied and tacit knowledge. Their singing sounds vastly different to the singing style generally heard today. This thesis examines vocal performance practice information preserved in written sources and early recordings. The practices examined are portamento, tempo rubato (rhythmical asynchrony and tempo modification), vibrato and messa di voce. The main goal is the re-enactment of the singing style from the decades preceding the recording era (extrapolating back to the 1850s). This has entailed a comprehensive analysis of a greater body of historical recordings than previously undertaken. Comparison between these recordings and written sources (annotated scores, instructive editions, vocal treatises, technical methods, concert reviews, correspondence, and biographies) provides in-depth understanding of practices and their application. For the practical application of this evidence, I have adopted a cyclical research process (recording emulation and experimental implementation of performance practice data), which has been used in previous research. Outcomes are presented in a practice-led case study: a recording of Schumann’s Dichterliebe (1840), a reimagining of the song cycle as it might have sounded in the decades immediately following its composition.

Cette thèse étudie les rapports entre l’expression d’attitudes agressives contrôlées et la perception de la dominance, à partir d’extraits de séances télévisées du conseil Municipal de Montreuil (93100) durant l’année 2013, période marquée par un climat politique vif et hostile. Un corpus a été constitué à partir d’extraits de parole spontanée de la Maire, Dominique Voynet, et de quatre de ses opposants. Les cinq locuteurs ont participé à l’enregistrement d’une relecture neutre du corpus de leurs propres extraits de parole (25 stimuli par locuteur) ainsi qu’à l’auto-évaluation perceptive de leurs stimuli (profils émotionnels), dont les résultats ont été comparés à l’évaluation perceptive des extraits par des auditeurs naïfs. Tous les locuteurs ont été perçus comme légèrement hostiles, légèrement mécontents et légèrement dominants malgré des profils émotionnels auto-évalués variables. Les extraits originaux et relus ont été comparés au niveau de leur structuration prosodico-syntaxique et de leurs caractéristiques temporelles et mélodiques. Les résultats montrent que 1) certains locuteurs semblent plus s’appuyer sur des paramètres mélodiques et d’autres sur des paramètres temporels ; 2) on peut néanmoins dégager les tendances générales concernant les corrélats dans la parole de l’hostilité et de la dominance dans notre corpus : a) des écarts entre structuration syntaxique et prosodique des extraits, b) la réduction ou l’absence d’allongements syllabiques finaux pré-pausaux, c) de fortes variations de plage de variation de F0 de part et d’autre des pauses silencieuses
This dissertation studies the relationship between the expression of controlled aggressive attitudes and the perception of dominance, based on extracts from televised sessions of the Municipal Council of Montreuil during 2013; a period marked by a lively and hostile political climate. We constituted a corpus of spontaneous speech extracts from the Mayor, Dominique Voynet, and four of her opponents. During subsequent recording sessions, the five speakers were asked to read transcriptions of their own speech extracts in a neutral tone (25 stimuli per speaker). They also participated in a self-evaluation questionnaire that focused on the perception of emotional profiles in their own stimuli. The results of the speakers’ perceptive evaluations were compared to those of a control group of naïve listeners. All speakers were perceived as slightly hostile, discontent and dominant, despite the variability observed in the self-evaluated profiles. The original and re-read extracts were compared in their prosodic- syntactic structure as well as their temporal and melodic characteristics. We show that: 1) some speakers seem to rely mostly on melodic parameters whereas others primarily use temporal parameters, 2) nevertheless, general trends emerge regarding the speech correlates of hostility and dominance in our corpus, notably: a) discrepancies between the syntactic and the prosodic structure of the extracts, b) reduction or absence of pre-pausal final syllabic lengthening, c) large variations in F0 range on both sides of silent pauses

A canção conta com o colorido das qualidades vocais de seus intérpretes, que através de diferentes sonoridades desempenham papel na expressividade e na construção de seu sentido. Dentre estas sonoridades estão as vozes-ruído, entendidas nesta pesquisa como qualidades vocais que apresentam ruído sonoro junto ao tom vocal. O presente estudo tem como objetivo investigar os aspectos intrínsecos do som proveniente de tais vozes - características fisiológicas, acústicas, psicoacústicas e psicodinâmicas -, e propor um levantamento de categoria, investigando sua relação com a expressividade da voz cantada através de uma escuta analítica. O recorte desta pesquisa compreende o modelo de canto popular brasileiro, no repertório do samba-canção da década de 1950, nas vozes de Dalva de Oliveira, Ângela Maria, Dolores Duran e Maysa. Os resultados apontam para o papel das qualidades vocais das intérpretes na construção do sentido da canção, onde a voz-ruído e sua sonoridade antagônica ajudam a delinear um estado emotivo expresso pela letra, assim como sugerem a identificação das cantoras às vertentes estéticas do samba-canção vigentes no período estudado.
The song counts on the color of the voice qualities of its performers, who through different sonorities play a role in expressiveness and in the construction of its meaning. Among these sonorities are the noise voices, understood in this research as voice qualities that present sonorous noise next to the vocal tone. The present study aims to investigate the intrinsic aspects of the sound coming from such voices - physiological, acoustic, psychoacoustic and psychodynamic characteristics - and to propose a category survey, investigating its relation with the expressiveness of the singing voice through an analytic listening. This research includes the popular Brazilian singing model, in the repertoire of the samba-canção of the 1950s, in the voices of Dalva de Oliveira, Ângela Maria, Dolores Duran and Maysa. The results point to the role of the voice qualities of the performers in the construction of the meaning of the song, where the noise voice and its antagonistic sonority help to delineate an emotional state expressed by the lyrics, as well as suggest the identification of the singers to the aesthetic aspects of the samba-canção during the study period.

The Introduction positions the history of girl and young woman singers in the 1960s in the context of broader histories of vocal training; ideas about voice, respectability, and expressivity; and the models of youthful femininity that were emergent in 1960s Britain. It opens with discussion of vocal discipline in magazines and books produced for young women. This is followed by reflections on the concept of voice as sound and voice as expression, how ideas about the use of voice are tied to gender, and how they have been used by feminist thinkers and scholars in the field of Voice Studies. Then, the introduction provides historical background on vocal pedagogy and histories of accent and vocal discipline in the UK, tying this history to the 1960s and notions of modernity that emerged at the time. It reflects on what voice and freedom of expression signified during the youth and musical movements of the “Swinging Sixties,” and, in particular, on how ideas about voice affected girls and young women in this period. Finally, it provides an overview of the book’s chapters provides an overview of the book’s chapters.

The Laban Workbook is a compendium of unique exercises inspired by the concepts and principles of movement theorist and artist, Rudolf Laban. Written by five internationally recognized movement experts, this textbook is divided into single-authored chapters, each of which includes a short contextual essay followed by a series of insight-bearing exercises. These expert views, honed in the creation of individual approaches to training and coaching actors, provide a versatile range of theory and practice in the creative process of crafting theatre. Readers will learn: Enhanced expressivity of body and voice; Clearer storytelling, both physical and vocal, facilitating the embodiment of playwrights’ intentions; Imaginative possibilities for exploring an existing play or for creating devised theatre. Featuring many exercises exploring the application of Laban Movement Studies to text, character, scene work, and devised performances - as well as revealing the creative potential of the body itself - The Laban Workbook is ideal for actors, teachers, directors and choreographers.

The epilogue ties the arguments about vocal expressivity and agency advanced in the previous chapters to questions about accountability, gender, and power raised by recent reports of sexual violence in the music industry. In 2012, Operation Yewtree revealed that high profile celebrities had used their power in the entertainment industry to abuse young people beginning in the 1960s. I ask how the notions of vocal expressivity and sexual liberation that emerged in the 1960s may have enabled these kinds of abuses. This epilogue reflects on how feminist music scholars and critics might honor expressions of agency while condemning abuse. It offers concluding thoughts on how music scholars can listen for agency and demand accountability.

The Introduction positions the history of girl and young woman singers in the 1960s in the context of broader histories of vocal training; ideas about voice, respectability, and expressivity; and the models of youthful femininity that were emergent in 1960s Britain. It opens with discussion of vocal discipline in magazines and books produced for young women. This is followed by reflections on the concept of voice as sound and voice as expression, how ideas about the use of voice are tied to gender, and how they have been used by feminist thinkers and scholars in the field of Voice Studies. Then, the introduction provides historical background on vocal pedagogy and histories of accent and vocal discipline in the UK, tying this history to the 1960s and notions of modernity that emerged at the time. It reflects on what voice and freedom of expression signified during the youth and musical movements of the “Swinging Sixties,” and, in particular, on how ideas about voice affected girls and young women in this period. Finally, it provides an overview of the book’s chapters provides an overview of the book’s chapters.

Abstract Idiosyncracies are to be encountered in every language; French is no exception. When it comes to singing in French, several features constitute topics particularly worthy of exploration. This chapter provides instruction on the most important of these topics. Emphatic stress (l’acccent d’insistance) involves shifting stress to a new syllable in the phonetic group in order to create a sense of urgency. This practice is widespread both in speech and in fine French singing. Another special topic is vocalic harmonization (l’harmonisation vocalique). Here, a relatively open vowel in an unstressed syllable closes to match the more closed vowel of the following, stressed syllable. This occurs in everyday French speech, but is applied much more cautiously in French vocal music. Unlike the other main singing languages, French rarely features consonant doubling (gémination consonantique). It is however possible in a few important scenarios, namely: in certain prefixes, with doubled (rolled) r in passages of heightened expressivity and in particular verb tenses, and as phrasal doubling of the same consonant in two words. An account is given for all of these cases. Several words with variable pronunciation are treated, including toujours, tous, and the infamously tricky word donc. The pronunciation of French numbers ends the chapter. Explanations and musical examples provide context.

This chapter discusses the role of performer additions in mid-seventeenth-century English song. It re-examines the relationship between delivery of a poetic text and musical performance. The ‘Hilton’ Songbook, BL Additional Manuscript 11608, demonstrates how a group of professional singers learned their ornamentation techniques from Italian sources such as Giulio Caccini, and how vocal expressivity could be achieved by breaking the customary rules of verbal rhetoric. Songs by Henry and William Lawes, Nicholas Lanier and Thomas Brewer, as well as theatrical music by Robert Johnson, are seen in varying stages of textual completion, allowing performers to insert themselves into the relationship between poets and composers. The results contradict the prevailing view of simplicity, artlessness and even musical decline that have often characterised descriptions of mid-seventeenth-century English song.

This chapter asks how American singer P. P. Arnold’s vocal performances in the 1960s shaped British popular music production and how she renarrates rock history today. The story of Arnold’s music career reveals how the Black feminine vocality exemplified by Arnold’s style of singing shaped 1960s rock, and how Black women singers navigate experiences of marginalization and narratives of authenticity. Arnold’s recordings for Immediate Records and her work with the Small Faces on songs like “Tin Soldier” reveal how this dynamic manifests musically, while the story of her “lost” album The Turning Tide illustrates the effect that it had on her career. The chapter closes with a section on Arnold’s recent live performances, using Black feminist thought to understand the implications of Arnold’s engagement with 1960s stereotypes of rock authenticity and sexual expressivity in her new work.