Academic literature on the topic 'Speech reinforcement'

Speech coding is an essential technology for digital cellular communications, voice over IP, and video conferencing systems. For more than 25 years, the main approach to speech coding for these applications has been block-based analysis-by-synthesis linear predictive coding. An alternative approach that has been less successful is sample-by-sample tree coding of speech. We reformulate this latter approach as a multistage reinforcement learning problem with L step lookahead that incorporates exploration and exploitation to adapt model parameters and to control the speech analysis/synthesis process on a sample-by-sample basis. The minimization of the spectrally shaped reconstruction error to finite depth manages complexity and serves as an effective stand in for the overall subjective evaluation of reconstructed speech quality and intelligibility. Different control policies that attempt to persistently excite the system states and that encourage exploration are studied and evaluated. The resulting methods produce reconstructed speech quality competitive with the most popular speech codec utilized today. This new reinforcement learning formulation provides new insights and opens up new directions for system design and performance improvement.

This research was due to some problems found in MTsS Darul Makmur. First, some students were not motivated in learning. Second, sometime the teacher still uses Indonesian in giving reinforcements. Third, some Students did not care about the teacher's reinforcement. This study aimed to find out the types of reinforcement used by the teacher. Then, to find out the types of reinforcement often and rarely to be usedby the teacher. Then, to find out the reasons the teacher used certain reinforcements. Last, to find out how the teacher understands the reinforcement. This research used a qualitative approach. The design of this research was descriptive because the researcher made a description of the use of reinforcement by theteacher in the English classroom. In this research, the interview and observation sheets were used by the researcher. The researcher found that the type of reinforcement used by the teacher is positive reinforcement and negative reinforcement. First, there were two types of positive reinforcement used by teachers, namely verbal reinforcement and non-verbal reinforcement. The verbal often used by theteacher was a reinforcement in the form of words and reinforcement in the form of phrases. Then, verbal reinforcement in the form of sentences was never done by the teacher in the learning process. While the non-verbal reinforcement often used by the teacher was gestural, activity reinforcement, and proximity reinforcement. Second, the negative reinforcement often used by the teacher was a warning, gesture, and eye contact. Meanwhile, the negative reinforcement rarely used by the teacher was speech volume andpunishment. Third, the reasons teachers reinforce learning are to motivate students and make students feel appreciated and happy while learning.

In this paper, we address the problem of howling detection in speech reinforcement system applications for utilization in howling control mechanisms. A general speech reinforcement system acquires speech from a speaker’s microphone, and delivers a reinforced speech to other listeners in the same room, or another room, through loudspeakers. The amount of gain that can be applied to the acquired speech in the closed-loop system is constrained by electro-acoustic coupling in the system, manifested in howling noises appearing as a result of acoustic feedback. A howling detection algorithm aims to early detect frequency-howls in the system, before the human ear notices. The proposed algorithm includes two cascaded stages: Soft Howling Detection and Howling False-Alarm Detection. The Soft Howling Detection is based on the temporal magnitude-slope-deviation measure, identifying potential candidate frequency-howls. Inspired by the temporal approach, the Howling False-Alarm Detection stage considers the understanding of speech-signal frequency components’ magnitude behavior under different levels of acoustic feedback. A comprehensive howling detection performance evaluation process is designed, examining the proposed algorithm in terms of detection accuracy and the time it takes for detection, under a devised set of howling scenarios. The performance improvement of the proposed algorithm, with respect to a plain magnitude-slope-deviation-based method, is demonstrated by showing faster detection response times over a set of howling change-rate configurations. The two-staged proposed algorithm also provides a significant recall improvement, while improving the precision decrease via the Howling False-Alarm Detection stage.

Text-to-Speech synthesis (TTS) can be used to generate training data for building Automatic Speech Recognition models (ASR). Access to medical speech data is because it is sensitive data that is difficult to obtain for privacy reasons. Speech can be synthesized by mimicking different accents, dialects, and speaking styles in a medical language. Reinforcement Learning (RL), in the context of ASR, can be used to optimize a model. A model can be trained to minimize errors in speech-to-text transcription, especially for technical medical terminology. In this case, the “reward” to the RL model can be negatively proportional to the number of transcription errors. The paper presents a method and experimental study from which it is concluded that the combination of TTS and RL can enable the creation of a speech recognition model suited to the specific needs of medical personnel, helping to expand the training data and optimize the model to minimize transcription errors. The learning process used reward functions based on Mean Opinion Score (MOS), a subjective metric for assessing speech quality, and Word Error Rate (WER), which evaluates the quality of speech-to-text transcription. [The Polish National Center for Research and Development (NCBR) supported the project: “ADMEDVOICE- Adaptive intelligent speech processing system of medical personnel with the structuring of test results and support of therapeutic process,” no. INFOSTRATEG4/0003/2022.]

This dissertation describes the development of an evaluation tool that can be used by an acoustican during the design stage of enclosures used for unassisted speech. Enclosures include lecture theatres, lecture halls and speech auditoriums. The tool is designed to enable Acousticians to be able to manipulate various acoustical parameters such as the geometry and the materials or construction selection to gauge the impact on speech performance. The tool can also be used to evaluate the performance of speech privacy within spaces using the Speech Transmission Index. Computer simulation tools have a number of advantages over existing methods such as physical scale models for this type of evaluation. Typical advantages are in the elimination of the difficult selection of materials with appropriate scale model acoustic performance, resolution of air absorption at scale model frequencies, reduced cost in development of the model, no storage space problems, ease of modifying and duplicating the model. Scale models also present difficulties in measuring some of the indices such as Speech Transmission Index. Whilst equipment can be purchased for the measurement of STI, scale model equivalents and the impact of the change in frequencies and modulations have not been researched or published.Currently, there are only two methods of evaluating the Speech Transmission of an enclosure: Build a full size enclosure and test; or simulate mathematically to derive the performance. At the time this thesis was commenced there were no commercial simulation programs available that could derive Speech Transmission Index information. The evaluation tool has been implemented as a computer program, based on IBM PC type computers running Microsoft WINDOWS 3.1 or later. The implementation uses the image method for the 'ray trace' algorithm. This basic image method utilises the enhancements made by a number of authors. In particular the Transformation Matrix method and homogenous coordinates have been used to improve the speed of the algorithm. Pre-computation of mutually invisible planes allows trimming the number of possible combination of rays that need to be computed. Results of physical measurement from two case studies have been compared to results of the simulation. Good correlation between the simulations and the case studies were achieved for the Speech Transmission Index and RASTI values. The accuracy of the simulation,in terms of decay based indices, is limited by the lack of sufficient tail to the calculated number of rays. Further research and implementation of hybrid techniques utilising both the image method and more traditional ray-tracing algorithms to improve the quality of the calculated decay data are required. Investigation of techniques used in photo-realism 'ray-tracing' may result in far more realistic data which is the basic input to the Speech Transmission Index calculations.

This dissertation describes the development of an evaluation tool that can be used by an acoustican during the design stage of enclosures used for unassisted speech. Enclosures include lecture theatres, lecture halls and speech auditoriums. The tool is designed to enable Acousticians to be able to manipulate various acoustical parameters such as the geometry and the materials or construction selection to gauge the impact on speech performance. The tool can also be used to evaluate the performance of speech privacy within spaces using the Speech Transmission Index. Computer simulation tools have a number of advantages over existing methods such as physical scale models for this type of evaluation. Typical advantages are in the elimination of the difficult selection of materials with appropriate scale model acoustic performance, resolution of air absorption at scale model frequencies, reduced cost in development of the model, no storage space problems, ease of modifying and duplicating the model. Scale models also present difficulties in measuring some of the indices such as Speech Transmission Index. Whilst equipment can be purchased for the measurement of STI, scale model equivalents and the impact of the change in frequencies and modulations have not been researched or published.
Currently, there are only two methods of evaluating the Speech Transmission of an enclosure: Build a full size enclosure and test; or simulate mathematically to derive the performance. At the time this thesis was commenced there were no commercial simulation programs available that could derive Speech Transmission Index information. The evaluation tool has been implemented as a computer program, based on IBM PC type computers running Microsoft WINDOWS 3.1 or later. The implementation uses the image method for the 'ray trace' algorithm. This basic image method utilises the enhancements made by a number of authors. In particular the Transformation Matrix method and homogenous coordinates have been used to improve the speed of the algorithm. Pre-computation of mutually invisible planes allows trimming the number of possible combination of rays that need to be computed. Results of physical measurement from two case studies have been compared to results of the simulation. Good correlation between the simulations and the case studies were achieved for the Speech Transmission Index and RASTI values. The accuracy of the simulation,in terms of decay based indices, is limited by the lack of sufficient tail to the calculated number of rays. Further research and implementation of hybrid techniques utilising both the image method and more traditional ray-tracing algorithms to improve the quality of the calculated decay data are required. Investigation of techniques used in photo-realism 'ray-tracing' may result in far more realistic data which is the basic input to the Speech Transmission Index calculations.

Deficits in conversation skills can be one barrier to developing and maintaining relationships for individuals with autism spectrum disorder (ASD). Individuals with ASD may deter conversation partners if they do not stay on topic or if they dwell on topics. Several interventions have been identified in targeting the reduction of problematic (off-topic or perseverative) speech, and withheld attention for its occurrence. In addition to leveraging attention as a reinforcer, one study provided signaled access to preferred topics contingent on talking about non-perseverative or therapist-selected topics. Despite showing clear improvements in on-topic speech and stimulus control of preferred topics, little is known about the additive effects of including contingent access to preferred topics. A free operant assessment was used to evaluate participant preference for including access to preferred topics. The results indicated that participants preferred the proposed intervention with access to a leisure item.

This case study evaluated the effects of differential reinforcement of other behavior (DRO) on scripting in a four year-old child with Autism Spectrum Disorder, Obsessive Compulsive Disorder and Celiac Disease. The overall goal was to show that DRO as the only independent variable could reduce scripting in a child with autism. A vibrator was set to vibrate every six minutes to indicate the end of each interval during intervention and the behavior was measured using a partial-interval time sampling method during the two hour in-home private Applied Behavior Analysis session over a two month period. An A-BC-C design demonstrated that DRO successfully decreased scripting behavior in the child with autism. A dependent paired samples t-test was used to compare the rates of scripting during the first three days of baseline and last three days of intervention. Results demonstrated a 29% decrease in scripting behavior. This result extends previous research that showed DRO, within a combined intervention, could be effective in decreasing scripting of adolescents with autism.

This research is motivated by the benefits that knowledge regarding early development in infants may provide to different fields of science. In particular, early sensorimotor exploration behaviors are studied in the framework of developmental robotics. The main objective is about understanding the role of motor constraint awareness and imitative behaviors during sensorimotor exploration. Particular emphasis is placed on prelinguistic vocal development because during this stage infants start to master the motor systems that will later allow them to pronounce their first words. Previous works have demonstrated that goal-directed intrinsically motivated sensorimotor exploration is an essential element for sensorimotor control learning. Moreover, evidence coming from biological sciences strongly suggests that knowledge acquisition is shaped by the environment in which an agent is embedded and the embodiment of the agent itself, including developmental processes that shape what can be learned and when. In this dissertation, we firstly provide a collection of theoretical evidence that supports the relevance of our study. Starting from concepts of cognitive and developmental sciences, we arrived al the conclusion that spoken language, i.e., early \/ocal development, must be studied asan embodied and situated phenomena. Considering a synthetic approach allow us to use robots and realistic simulators as artifacts to study natural cognitive phenomena. In this work, we adopta toy example to test our cognitive architectures and a speech synthesizer that mimics the mechanisms by which humans produce speech. Next, we introduce a mechanism to endow embodied agents with motor constraint awareness. lntrinsic motivation has been studied as an importan! element to explain the emergence of structured developmental stages during early vocal development. However, previous studies failed to acknowledge the constraints imposed by the embodiment and situatedness, al sensory, motor, cognitive and social levels. We assume that during the onset of sensorimotor exploratory behaviors, motor constraints are unknown to the developmental agent. Thus, the agent must discover and learn during exploration what !hose motor constraints are. The agent is endowed with a somesthetic system based on tactile information. This system generales a sensor signal indicating if a motor configuration was reached or not. This information is later used to create a somesthetic model to predict constraint violations. Finally, we propase to include social reinforcement during exploration. Sorne works studying early vocal development have shown that environmental speech shapes the sensory space explored during babbling. More generally, imitative behaviors have been demonstrated to be crucial for early development in children as they constraint the search space.during sensorimotor exploration. Therefore, based on early interactions of infants and caregivers we proposed an imitative mechanism to reinforce intrinsically motivated sensorimotor exploration with relevan! sensory units. Thus, we modified the constraints aware sensorimotor exploration architecture to include a social instructor, expert in sensor units relevant to communication, which interacts with the developmental agent. lnteraction occurs when the learner production is ·enough' similar to one relevan! to communication. In that case, the instructor perceives this similitude and reformulates with the relevan! sensor unit. When the learner perceives an utterance by the instructor, it attempts to imitate it. In general, our results suggest that somesthetic senses and social reinforcement contribute to achieving better results during intrinsically motivated exploration. Achieving lest redundant exploration, decreasing exploration and evaluation errors, as well as showing a clearer picture of developmental transitions.
La motivación principal de este trabajo es la magnitud que las contribuciones al conocimiento en relación al desarrollo infantil pueden aportar a diferentes campos de la ciencia. Particularmente, este trabajo se enfoca en el estudio de los comportamientos de autoexploración sensorimotora en un marco robótico e inspirado en el campo de la psicología del desarrollo. Nuestro objetivo principal es entender el papel que juegan las restricciones motoras y los reflejos imitativos durante la exploración espontánea observada en infantes. Así mismo, este trabajo hace especial énfasis en el desarrollo vocal-auditivo en infantes, que les provee con las herramientas que les permitirán producir sus primeras palabras. Trabajos anteriores han demostrado que los comportamientos de autoexploración sensorimotora en niños, la cual ocurre en gran medida por motivaciones intrínsecas, es un elemento importante para aprender a controlar su cuerpo con tal de alcanzar estados sensoriales específicos. Además, evidencia obtenida de estudios biológicos sugiere tajantemente que la adquisición de conocimiento es regulada por el ambiente en el cual un agente cognitivo se desenvuelve y por el cuerpo del agente per se. Incluso, los procesos de desarrollo que ocurren a nivel físico, cognitivo y social también regulan que es aprendido y cuando esto es aprendido. La primera parte de este trabajo provee al lector con la evidencia teórica y práctica que demuestran la relevancia de esta investigación. Recorriendo conceptos que van desde las ciencias cognitivas y del desarrollo, llegamos a la conclusión de que el lenguaje, y por tanto el habla, deben ser estudiados como fenómenos cognitivos que requieren un cuerpo físico y además un ambiente propicio para su existencia. En la actualidad los sistemas robóticos, reales y simulados, pueden ser considerados como elementos para el estudio de los fenómenos cognitivos naturales. En este trabajo consideramos un ejemplo simple para probar las arquitecturas cognitivas que proponemos, y posteriormente utilizamos dichas arquitecturas con un sintetizador de voz similar al mecanismo humano de producción del habla. Como primera contribución de este trabajo proponemos introducir un mecanismo para construir robots capaces de considerar sus propias restricciones motoras durante la etapa de autoexploración sensorimotora. Ciertos mecanismos de motivación intrínseca para exploración sensorimotora han sido estudiados como posibles conductores de las trayectorias de desarrollo observadas durante el desarrollo temprano del habla. Sin embargo, en previos estudios no se consideró o que este desarrollo está a delimitado por restricciones debido al ambiente, al cuerpo físico, y a las capacidades sensoriales, motoras y cognitivas. En nuestra arquitectura, asumimos que un agente artificial no cuenta con conocimiento de sus limitantes motoras, y por tanto debe descubrirlas durante la etapa de autoexploración. Para tal efecto, el agente es proveído de un sistema somatosensorial que le indica cuando una configuración motora viola las restricciones impuestas por el propio cuerpo. Finalmente, como segunda parte de nuestra contribución proponemos incluir un mecanismo para reforzar el aprendizaje durante la autoexploración. Estudios anteriores demostraron que el ambiente lingüístico en que se desarrolla un infante, o un agente artificial, condiciona sus producciones vocales durante la autoexploración o balbuceo. En este trabajo nos enfocamos en el estudio de episodios de imitación que ocurren durante el desarrollo temprano de un agente. Basados en estudios sobre la interacción entre madres e hijos durante la etapa pre lingüística, proponemos un mecanismo para reforzar el aprendizaje durante la autoexploración con unidades sensoriales relevantes. Entonces, a partir de la arquitectura con autoconocimiento de restricciones motores, construimos una arquitectura que incluye un instructor experto en control sensorimotor. Las interacciones entre el aprendiz y el experto ocurren cuando el aprendiz produce una unidad sensorial relevante para la comunicación durante la autoexploración. En este caso, el experto percibe esta similitud y responde reformulando la producción del aprendiz como la unidad relevante. Cuando el aprendiz percibe una acción del experto, inmediatamente intenta imitarlo. Los resultados presentados en este trabajo sugieren que, los sistemas somatosensoriales, y el reforzamiento social contribuyen a lograr mejores resultados durante la etapa de autoexploración sensorimotora motivada intrínsecamente. En este sentido, se logra una exploración menos redundante, los errores de exploración y evaluación disminuyen, y por último se obtiene una imagen más nítida de las transiciones entre etapas del desarrollo.
La motivació principal d'aquest treball és la magnitud que les contribucions al coneixement en relació al desenvolupament infantil poden aportar a diferents camps de la ciència. Particularment, aquest treball s'enfoca en l'estudi dels comportaments d’autoexploració sensorimotora en un marc robòtic i inspirat en el camp de la psicologia del desenvolupament. El nostre objectiu principal és entendre el paper que juguen les restriccions motores i els reflexos imitatius durant l’exploració espontània observada en infants. Així mateix, aquest treball fa especial èmfasi en el desenvolupament vocal-auditiu en infants, que els proveeix amb les eines que els permetran produir les seves primeres paraules. Treballs anteriors han demostrat que els comportaments d'autoexploració sensorimotora en nens, la qual ocorre en gran mesura per motivacions intrínseques, és un element important per aprendre a controlar el seu cos per tal d'assolir estats sensorials específics. A més, evidencies obtingudes d'estudis biològics suggereixen que l’adquisició de coneixement és regulada per l'ambient en el qual un agent cognitiu es desenvolupa i pel cos de l'agent per se. Fins i tot, els processos de desenvolupament que ocorren a nivell físic, cognitiu i social també regulen què és après i quan això ès après. La primera part d'aquest treball proveeix el lector amb les evidencies teòrica i pràctica que demostren la rellevància d'aquesta investigació. Recorrent conceptes que van des de les ciències cognitives i del desenvolupament, vam arribar a la conclusió que el llenguatge, i per tant la parla, han de ser estudiats com a fenòmens cognitius que requereixen un cos físic i a més un ambient propici per a la seva existència. En l'actualitat els sistemes robòtics, reals i simulats, poden ser considerats com a elements per a l'estudi dels fenòmens cognitius naturals. En aquest treball considerem un exemple simple per provar les arquitectures cognitives que proposem, i posteriorment utilitzem aquestes arquitectures amb un sintetitzador de veu similar al mecanisme humà de producció de la parla. Com a primera contribució d'aquest treball proposem introduir un mecanisme per construir robots capaços de considerar les seves pròpies restriccions motores durant l'etapa d'autoexploració sensorimotora. Certs mecanismes de motivació intrínseca per exploració sensorimotora han estat estudiats com a possibles conductors de les trajectòries de desenvolupament observades durant el desenvolupament primerenc de la parla. No obstant això, en previs estudis no es va considerar que aquest desenvolupament és delimitat per restriccions a causa de l'ambient, el cos físic, i les capacitats sensorials, motores i cognitives. A la nostra arquitectura, assumim que un agent artificial no compta amb coneixement dels seus limitants motors, i per tant ha de descobrir-los durant l'etapa d'autoexploració. Per a tal efecte, l'agent és proveït d'un sistema somatosensorial que li indica quan una configuració motora viola les restriccions imposades pel propi cos. Finalment, com a segona part de la nostra contribució proposem incloure un mecanisme per reforçar l'aprenentatge durant l'autoexploració. Estudis anteriors han demostrat que l'ambient lingüísticstic en què es desenvolupa un infant, o un agent artificial, condiciona les seves produccions vocals durant l'autoexploració o balboteig. En aquest treball ens enfoquem en l'estudi d'episodis d’imitació que ocorren durant el desenvolupament primerenc d'un agent. Basats en estudis sobre la interacció entre mares i fills durant l'etapa prelingüística, proposem un mecanisme per reforçar l'aprenentatge durant l'autoexploració amb unitats sensorials rellevants. Aleshores, a partir de l'arquitectura amb autoconeixement de restriccions motors, vam construir una arquitectura que inclou un instructor expert en control sensorimotor. Les interaccions entre l'aprenent i l'expert, ocorren quan una producció sensorial de l'aprenent durant l'autoexploració és similar a una unitat sensorial rellevant per a la comunicació. En aquest cas, l'expert percep aquesta similitud i respon reformulant la producció de l'aprenent com la unitat rellevant. Quan l'aprenent percep una acció de l'expert, immediatament intenta imitar-lo. Els resultats presentats en aquest treball suggereixen que els sistemes somatosensorials i el reforçament social contribueixen a aconseguir millors resultats durant l'etapa d'autoexploració sensorimotora motivada intrínsecament. En aquest sentit, s'aconsegueix una exploració menys redundant, els errors d’exploració i avaluació disminueixen, i finalment s’obté una imatge més nítida de les transicions entre etapes del desenvolupament

The overall aim of the current research was to investigate the corticostriatal system in developmental language impairment (DLI) at the behavioral and neuroanatomical levels. Two groups of young adults, one with DLI (N = 25) and the other without (N = 23), participated in the behavioral study. A sample of procedural learning and reinforcement learning (RL) tasks was selected. Each task represents a unique aspect of procedural memory, and learning processes during these tasks have been linked, at least partially, to the functionality of the corticostriatal system. Findings showed that individuals with DLI demonstrated relatively poor performance on different aspects of procedural learning and on RL. Correlation results provide further evidence for a close relationship between individual differences in implicit learning and individual differences in language. These results implicate an abnormal corticostriatal system in DLI. In the structural imaging study, two subgroups of participants from the first study, one with DLI (n = 10) and the other without (n = 10), were matched on age, gender, and handedness. Conventional magnetic resonance imaging (MRI) and diffusion tensor imaging (DTI) were used to investigate the subcortical components of the corticostriatal system in individuals with DLI. Results showed pathological enlargement in the bilateral putamen, the right globus pallidus, and the bilateral nucleus accumbens of individuals with DLI. In addition, the DLI group revealed decreased FA in the globus pallidus and in the thalamus, indicating abnormal white matter integrity in the two subcortical regions. These imaging results underpin the behavioral results, showing corticostriatal abnormalities in DLI at both macrostructural and microstructural levels. In addition to subcortical regions, the four cerebral lobes were also included for an exploratory analysis. Findings showed that individuals with DLI had global diffusion abnormalities in cerebral white matters in the absence of volumetric alterations, and these abnormalities were closely associated with impaired language performance. The results support a role of white matter integrity in language function. In conclusion, individuals with DLI have an abnormal corticostriatal system, which may lead to compromise of a wide variety of cognitive learning, including procedural learning, RL, and certain aspects of language learning.

La quantité de diffusion de signaux de parole dans les habitacles automobiles est de plus en plus importante : télécommunications, radio, système de navigation... Cependant, malgré les efforts et les avancées mécaniques, beaucoup de bruits persistent au sein de l'habitacle dégradant fortement l'intelligibilité de ces signaux de parole. L'objectif de cette thèse est alors de développer des outils de renforcement de la parole visant à traiter les signaux avant leur dégradation afin d'assurer une bonne intelligibilité dans le bruit des habitacles automobiles. Une approche de renforcement de la parole très performante consiste à utiliser un égaliseur fréquentiel afin d’optimiser un critère d’intelligibilité : le Speech Intelligibility Index (SII). Pour faciliter l'optimisation, les méthodes actuelles se basent sur des approximations du critère. De plus, en concentrant l'énergie spectrale du signal dans des zones où l'oreille est plus sensible, ces méthodes augmentent le volume perçu ce qui peut détériorer l'expérience utilisateur. Ainsi, en plus de proposer une méthode de résolution exacte du problème de maximisation du SII, nos travaux proposent d’introduire et étudier l'influence d'une nouvelle contrainte perceptive maintenant les signaux à leur niveau perçu. La popularisation des approches d’apprentissage automatique pousse à apprendre les traitements de renforcement de la parole à partir d’exemples naturellement produits dans le bruit (parole Lombard), ou en sur-articulant (parole claire). Les travaux actuels ne parviennent pas à obtenir des gains d’intelligibilité aussi significatifs qu’avec les modifications naturelles et nous pensons que la négligence de nombreux aspects temporels pourrait en être partiellement responsable. Nos travaux proposent donc d’approfondir ces approches en exploitant des modèles d’apprentissage et des pré-traitements adaptés aux séquences temporelles longues. Nous proposons aussi une nouvelle modélisation des modifications du débit de la parole directement intégrable dans l’apprentissage machine ce qui n'avait jamais été fait auparavant
Speech is nowadays present in a number of in-car applications ranging from hands-free communications, radio programs to speech synthesis messages from the various car devices.However, despite the steady car manufacturing progress, significant noise still remains in the car interior that leads to a loss of intelligibility of speech signals. The PhD work aims at developping speech reinforcement tools in order to process the signals before they are played in a noisy in-car environment.A highly effective speech reinforcement approach is to use a frequency equalizer to optimize an intelligibility criterion : the Speech Intelligibility Index (SII). To facilitate optimization, current methods are based on approximations of the criterion. In addition, by concentrating the spectral energy of the signal in areas where the ear is more sensitive, these methods increase the perceived volume which can deteriorate the user experience. Thus, in addition to proposing an exact method of solving the SII maximization problem, our work proposes to introduce and study the influence of a new perceptual constraint in order to maintain the signals at their perceived level.The popularization of machine learning approaches pushes to learn speech reinforcement processings from examples naturally produced in noise (Lombard speech), or by over-articulation (clear speech). Current work fails to achieve intelligibility gains as significant as with natural modification, and we believe that the many temporal aspects neglect may be partially responsible. Our work therefore proposes to deepen these approaches by exploiting learning models and pre-processings adapted to long duration sequences. We also propose a new modeling of the speech rate modifications that directly fits in the machine learning model which had never been done before

Vehicles driving in the urban settings experience substantial disturbances from neighbouring vehicles and traffic signals. Deviating from the optimal trajectory causes excessive fuel consumption and delay. This research proposes a novel adaptive driving-speed-control algorithm using a Reinforcement Learning (Q-learning) approach. The proposed algorithm can respond to the prevailing traffic conditions and traffic-controls conditions at signalised intersection environment and provides the control vehicle with target driving-speeds to achieve fuel savings. The micro-simulation results confirm the effectiveness of the algorithm by significantly and consistently reducing the fuel consumption of the control vehicle under varying driving environments.