Tesis sobre el tema "Distant speech"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores tesis para su investigación sobre el tema "Distant speech".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
Ravanelli, Mirco. "Deep Learning for Distant Speech Recognition". Doctoral thesis, Università degli studi di Trento, 2017. https://hdl.handle.net/11572/368959.
Texto completoRavanelli, Mirco. "Deep Learning for Distant Speech Recognition". Doctoral thesis, University of Trento, 2017. http://eprints-phd.biblio.unitn.it/2693/1/PhD_thesis_Ravanelli_Mirco_archived.pdf.
Texto completoLiu, Yulan. "Distant speech recognition of natural spontaneous multi-party conversations". Thesis, University of Sheffield, 2017. http://etheses.whiterose.ac.uk/17691/.
Texto completoMahdian, Toroghi Rahil [Verfasser] y Dietrich [Akademischer Betreuer] Klakow. "Blind speech separation in distant speech recognition front-end processing / Rahil Mahdian Toroghi ; Betreuer: Dietrich Klakow". Saarbrücken : Saarländische Universitäts- und Landesbibliothek, 2016. http://d-nb.info/1119802229/34.
Texto completoEldridge, Larry D. "A distant heritage : the growth of free speech in early America /". New York, NY [u.a.] : New York Univ. Press, 1994. http://www.gbv.de/dms/spk/sbb/recht/toc/277767857.pdf.
Texto completoTitus, Andrew Richard. "A study of adaptive enhancement methods for improved distant speech recognition". Thesis, Massachusetts Institute of Technology, 2018. http://hdl.handle.net/1721.1/119706.
Texto completoThis electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 65-68).
Automatic speech recognition systems trained on speech data recorded by microphones placed close to the speaker tend to perform poorly on speech recorded by microphones placed farther away from the speaker due to reverberation effects and background noise. I designed and implemented a variety of machine learning models to improve distant speech recognition performance by adaptively enhancing incoming speech to appear as if it was recorded in a close-talking environment, regardless of whether it was originally recorded in a close-talking or distant environment. These were evaluated by passing the enhanced speech to acoustic models trained on only close-talking speech and comparing error rates to those achieved without speech enhancement. Experiments conducted on the AMI, TIMIT and TED-LIUM datasets indicate that decreases in error rate on distant speech of up to 33% relative can be achieved by these with only minor increases (1% relative) on clean speech.
by Andrew Richard Titus.
M. Eng.
Guerrero, Flores Cristina Maritza. "Information Fusion Approaches for Distant Speech Recognition in a Multi-microphone Setting". Doctoral thesis, Università degli studi di Trento, 2016. https://hdl.handle.net/11572/368955.
Texto completoGuerrero, Flores Cristina Maritza. "Information Fusion Approaches for Distant Speech Recognition in a Multi-microphone Setting". Doctoral thesis, University of Trento, 2016. http://eprints-phd.biblio.unitn.it/1853/1/160830_cguerrero_phd-thesis.pdf.
Texto completoSwietojanski, Paweł. "Learning representations for speech recognition using artificial neural networks". Thesis, University of Edinburgh, 2016. http://hdl.handle.net/1842/22835.
Texto completoKITAOKA, Norihide, Seiichi NAKAGAWA y Longbiao WANG. "Robust Speech Recognition by Combining Short-Term and Long-Term Spectrum Based Position-Dependent CMN with Conventional CMN". Institute of Electronics, Information and Communication Engineers, 2008. http://hdl.handle.net/2237/14966.
Texto completoMariotte, Théo. "Traitement automatique de la parole en réunion par dissémination de capteurs". Electronic Thesis or Diss., Le Mans, 2024. http://www.theses.fr/2024LEMA1001.
Texto completoThis thesis work focuses on automatic speech processing, and more specifically on speaker diarization. This task requires the signal to be segmented to identify events such as voice activity, overlapped speech, or speaker changes. This work tackles the scenario where the signal is recorded by a device located in the center of a group of speakers, as in meetings. These conditions lead to a degradation in signal quality due to the distance between the speakers (distant speech).To mitigate this degradation, one approach is to record the signal using a microphone array. The resulting multichannel signal provides information on the spatial distribution of the acoustic field. Two lines of research are being explored for speech segmentation using microphone arrays.The first introduces a method combining acoustic features with spatial features. We propose a new set of features based on the circular harmonics expansion. This approach improves segmentation performance under distant speech conditions while reducing the number of model parameters and improving robustness in case of change in the array geometry.The second proposes several approaches that combine channels using self-attention. Different models, inspired by an existing architecture, are developed. Combining channels also improves segmentation under distant speech conditions. Two of these approaches make feature extraction more interpretable. The proposed distant speech segmentation systems also improve speaker diarization.Channel combination shows poor robustness to changes in the array geometry during inference. To avoid this behavior, a learning procedure is proposed, which improves the robustness in case of array mismatch.Finally, we identified a gap in the public datasets available for distant multichannel automatic speech processing. An acquisition protocol is introduced to build a new dataset, integrating speaker position annotation in addition to speaker diarization.Thus, this work aims to improve the quality of multichannel distant speech segmentation. The proposed methods exploit the spatial information provided by microphone arrays while improving the robustness in case of array mismatch
Miller, Carol Jane. "Distance education for professional development : a case study". Thesis, Open University, 1997. http://oro.open.ac.uk/56478/.
Texto completoHarrell, Dameon C. (Dameon Cartíer) 1976. "Effects of microphone type and distance upon the spectra of speech sounds". Thesis, Massachusetts Institute of Technology, 1999. http://hdl.handle.net/1721.1/80067.
Texto completoIncludes bibliographical references (leaf 71).
by Dameon C. Harrell.
S.B.and M.Eng.
West, Paula. "Long-distance coarticulatory effects of English /l/ and /r/". Thesis, University of Oxford, 2000. http://ora.ox.ac.uk/objects/uuid:52cb3c89-6ec9-4f21-b219-aae92c0c6660.
Texto completoWilliams, A. Lynn. "From Developmental Norms to Distance Metrics: Target Selection Factors and Criteria". Digital Commons @ East Tennessee State University, 2005. https://www.amzn.com/1557667845/.
Texto completoMashima, Pauline A. "The Use of Video-Teleconferencing to Deliver Voice Therapy At-A-Distance". University of Cincinnati / OhioLINK, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1299182897.
Texto completoChiou, Greg I. "Active contour models for distinct feature tracking and lipreading /". Thesis, Connect to this title online; UW restricted, 1995. http://hdl.handle.net/1773/6023.
Texto completoFux, Thibaut. "Vers un système indiquant la distance d'un locuteur par transformation de sa voix". Thesis, Grenoble, 2012. http://www.theses.fr/2012GRENT120/document.
Texto completoThis thesis focuses on speaker voice transformation in the aim to indicate the distance of it: a spokento-whispered voice transformation to indicate a close distance and a spoken-to-shouted voicetransformation for a rather far distance. We perform at first, in-depth analysis to determine mostrelevant features in whispered voices and especially in shouted voices (much harder). The maincontribution of this part is to show the relevance of prosodic parameters in the perception of vocaleffort in a shouted voice. Then, we propose some descriptors to better characterize the prosodiccontours. For the actual transformation, we propose several new transformation rules whichimportantly control the quality of transformed voice. The results showed a very good quality oftransformed whispered voices and transformed shouted voices for relatively simple linguisticstructures (CVC, CVCV, etc.)
Madison, Curtis John. "The politics of discourse design: Distance delivery of education by two-way video in Alaska". Diss., The University of Arizona, 1999. http://hdl.handle.net/10150/289055.
Texto completoSooful, Jayren Jugpal. "Automated phoneme mapping for cross-language speech recognition". Diss., Pretoria [s.n.], 2004. http://upetd.up.ac.za/thesis/available/etd-01112005-131128.
Texto completoLiang, Hongkang. "Statistics of nonlinear averaging spectral estimators and a novel distance measure for HMMs with application to speech quality estimation". Laramie, Wyo. : University of Wyoming, 2005. http://proquest.umi.com/pqdweb?did=1031050291&sid=1&Fmt=2&clientId=18949&RQT=309&VName=PQD.
Texto completoBennett, Benjamin. "Accurate Distance Calculation Using GPS While Performing Low Speed Activity". Thesis, University of Oregon, 2018. http://hdl.handle.net/1794/23827.
Texto completoEntz, Stephanie. "The effect of slow speech on tongue movements & acoustic vowel space distance in speakers with Amyotrophic Lateral Sclerosis". Thesis, Wichita State University, 2013. http://hdl.handle.net/10057/6813.
Texto completoThesis (M.A.)--Wichita State University, College of Health Professions, Dept. of Communication Sciences and Disorders
Williams, A. Lynn. "A Systematic Perspective for Assessment and Intervention: A Case Study". Digital Commons @ East Tennessee State University, 2006. https://dc.etsu.edu/etsu-works/2001.
Texto completoBushnell, Tyler Dwight. "A biomechanical analysis of sprinters vs. distance runners at equal and maximal speeds /". Diss., CLICK HERE for online access, 2004. http://contentdm.lib.byu.edu/ETD/image/etd634.pdf.
Texto completoBushnell, Tyler D. "A Biomechanical Analysis of Sprinters vs. Distance Runners at Equal and Maximal Speeds". BYU ScholarsArchive, 2004. https://scholarsarchive.byu.edu/etd/217.
Texto completoWilliams, A. Lynn. "Assessment, Target Selection, and Intervention: Dynamic Interactions Within a Systemic Perspective". Digital Commons @ East Tennessee State University, 2005. https://dc.etsu.edu/etsu-works/2002.
Texto completoNakayama, Masataka. "The problems of serial order in language:Clustering, context discrimination, temporal distance, and edges". Kyoto University, 2015. http://hdl.handle.net/2433/200480.
Texto completoCaygill, Matthew. "Public attitudes to long distance travel and perceptions of high speed rail". Thesis, University of Newcastle upon Tyne, 2014. http://hdl.handle.net/10443/2734.
Texto completoBerardi, Francesca. "Gli specchi e il labirinto tra distanza e alterità: Emilio Tadini traduttore di Shakespeare". Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2014. http://amslaurea.unibo.it/7133/.
Texto completoAndersson, Christoffer. "Golf swing rotational max power correlation to clubhead speed, ball speed and carry distance in young elite golf players". Thesis, Högskolan i Halmstad, Akademin för ekonomi, teknik och naturvetenskap, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-33896.
Texto completoReeve, Michelle. "Spider gait adaptation for speed and leg autotomy in two ecologically distinct species". Thesis, Royal Veterinary College (University of London), 2018. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.766339.
Texto completoSklar, Alexander Gabriel. "Channel Modeling Applied to Robust Automatic Speech Recognition". Scholarly Repository, 2007. http://scholarlyrepository.miami.edu/oa_theses/87.
Texto completoPacheco, Shaun, Chengliang Wang, Monica K. Chawla, Minhkhoi Nguyen, Brend K. Baggett, Urs Utzinger, Carol A. Barnes y Rongguang Liang. "High resolution, high speed, long working distance, large field of view confocal fluorescence microscope". NATURE PUBLISHING GROUP, 2017. http://hdl.handle.net/10150/625967.
Texto completoRees-Jones, Stephen Mark. "The use of peak running speed for performance monitoring of well-trained distance runners". Thesis, University of Sheffield, 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.408352.
Texto completoMunoz, Joshua. "Application of Multifunctional Doppler LIDAR for Non-contact Track Speed, Distance, and Curvature Assessment". Diss., Virginia Tech, 2015. http://hdl.handle.net/10919/77876.
Texto completoPh. D.
Corcoran, Briana Christine. "Duration and distance of hyoid bone movement as observed by ultrasound: The influences of flavor and nectar-thick consistency". Miami University / OhioLINK, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=miami1303160299.
Texto completoSalmi, Louiza. "Pertinence des normes et standards dans les dispositifs de formation à distance". Thesis, Strasbourg, 2012. http://www.theses.fr/2012STRAC036/document.
Texto completoThis thesis focuses on standardization in the field of distance learning. Among the many proposed standards, our interest focuses on the enrichment of latest standard proposal, which is the IMS-LD standard. We would therefore introduce the standardization relevance notion which means the ability of IMS-LD prescribes learning scenarios that actually meet certain educational principles. For our research, we focused on an essential component of learning (Leontiev, 1981), it is the motivation to learn. From this thesis, we obtained three main results validated by conducting case studies: first, is an activity theories’ posteriori design based approach; It describes, from traces, the actual learning activity scenario taking into account its human factors. The second result is a taxonomy based on the speech acts theory; it allowed us to translate some motivation components as a set of speech acts observed in « Chat » discussion. The third result is a motivation descriptive model that reflects, from the traces, the perceptions and their origins. This model uses our taxonomy and is based on the adjacency pairs concept derived from conversational analysis. Finally, our conclusions explain further, our secondary results and provide opportunities for continuing our question about standards relevance
Moreno, Anaïs. "Le discours rapporté dans les intéractions : l'effet de la proximité et des communautés de pratique sur sa construction à l'oral et à l'écrit". Thesis, Paris 10, 2016. http://www.theses.fr/2016PA100064/document.
Texto completoP. Koch & W. Œsterreicher's works questioned the spoken/written opposition in terms of a continuum (proximity/distance) beyond graphic or phonic characters of interactions. The communication situation widely influences the construction of the discourse, and it allows for the medium to be overshadowed. From this model, we will deal with the construction of reporteed speech, more specifically with the direct reported speech (DRD) in ordinary written and spoken interactions. DRD is very frequent in these interactions and appears as a centrepiece of the speaker's involvement. He said, I said... punctuate everyday conversations and allow for the introduction of reported utterances.The study of elements and their manifestation in the context of DRD (reporting verbs, discourse particles, punctuation, pauses...) and the framework used to indicate quoted speech, will allow for a more comprehensive understanding of DRD functioning. We will try to give account of the correlation between the choice of the structure, the presence or absence of certain items and the communication situation. To carry out this study, we have built a heterogeneous corpus which consists of several spoken and written interactions with different degrees of proximity (interviews, spontaneous conversations, forum posts, chat, anecdotes Vie de Merde). The aim of this study is to understand the paramaters entering into DRD's variation (appeal and form), beyond the spoken/written opposition
HAZOOR, ABRAR. "(Provisional) Development and Implementation of a Novel Intelligent Speed Adaptation System Based on Sight Distance". Doctoral thesis, Politecnico di Torino, 2022. https://hdl.handle.net/11583/2973432.
Texto completoJogineedi, Rohit. "Development of Comparative Wear Test of ASTM G75 Standard". OpenSIUC, 2017. https://opensiuc.lib.siu.edu/theses/2240.
Texto completoClaesson, Martin y Lovisa Edholm. "How Different Parameters Affect the Downlink Speed". Thesis, Linköpings universitet, Institutionen för datavetenskap, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-131484.
Texto completoCarnes, Andrew. "The effect of peer influence on running speed, enjoyment, and perceived exertion in intercollegiate distance runners". Kent State University / OhioLINK, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=kent1309360806.
Texto completoBelam, Patricia Viana. "Avaliação do website \'Voice assessment: speech-language pathology and audiology & medicine\', volume 1 - do Projeto Homem Virtual - no contexto de ensino e aprendizagem da língua inglesa". Universidade de São Paulo, 2014. http://www.teses.usp.br/teses/disponiveis/25/25143/tde-16072014-114803/.
Texto completoFollowing the increasing use of computer technologies in the areas of education and health, based on Distance Education proposals, the website Voice assessment: speech-language pathology and audiology & medicine was developed, based on the Portuguese version of the CD-ROM Voice assessment: speech-language pathology and audiology & medicine, Virtual Man Project, volume 1, developed in 2006, in a partnership between the University of São Paulo (USP) and the Federal University of São Paulo (UNIFESP). In this sense, this research aimed at evaluating its efficacy as an educational instrument concerning its cognitive and subjective aspects, in the context of English language teaching, more specifically in pronunciation teaching, being the last phase of the multicenter research project responsible for the website development and evaluation. 30 students participated in this research 15 from the Languages Teaching Course and 15 from the Translator Course at University of Sagrado Coração, in the city of Bauru, who were studying the subject English Phonetics and Phonology, whose teacher was the researcher. The group of 30 students was divided into 2 equal groups of 15 students, called Experimental Group which made use of the website as a complementary material for the subject, and the Control Group - which did not use the website. Data collection was carried out by means of two questionnaires, which gathered data related to the cognitive aspects the Pre-website Questionnaire and the Post-website Questionnaire, besides the Motivational Research Form, after the study. Three different means were used to access the website: tablet, smartphone and computer. For the comparison between the groups, considering each question and the number of right answers from each participant, the Fishers Exact Test and the Paired T- Test were used, respectively. For the comparison among the three different website access means, the Analysis of Variance was used followed by the Tukey Test. After the website study, results showed that the Experimental Group had a better performance in all the questions in relation to the Control Group, as well as a greater number of right answers per participant to the questions in the questionnaires. As to the access means, there was no significant statistical difference in the comparison among the three means when the difference between the number of right answers in the pre and post-website questionnaires was considered. In relation to the evaluation concerning the subjective aspects, assessed by the Motivational Research Form, data analysis revealed an Impressive website. Thus, the website showed efficacy as an educational instrument in relation to its evaluation both regarding the cognitive and the subjective aspects, independently of the means used. Nevertheless, further research is suggested aiming at expanding the use and evaluating the efficacy of the website in other contexts of English teaching in order to grant this Distance Education instrument greater quality and efficacy.
Wrobel, Shannon Alicia. "Multi-Function LIDAR Sensors for Non-Contact Speed and Track Geometry Measurement in Rail Vehicles". Thesis, Virginia Tech, 2013. http://hdl.handle.net/10919/23134.
Texto completoWheel-mounted tachometer speed measurements often fluctuate due to wheel vibrations, change in wheel diameter, or wheel slip affecting the measurement accuracy. Frequent calibrations are needed to account for changes in wheel diameter due to wear. Additionally, the high levels of vibrations at the wheel can cause occasional mechanical failure of the encoder.
This thesis examines LIDAR as a non-contact train speed measurement device as a direct retrofit for wheel-mounted encoders. LIDAR uses Doppler technology to accurately measure train speed. The LIDAR system consists of two laser sensors and can be installed on either the car body or the truck on the underside of the train. The sensors measure the true ground speed of each rail, from which the track curvature can then be assessed based on the difference between the right and left rail speeds. The LIDAR train speed, distance, and curvature results are then evaluated against encoder readings and other conventional train measurement devices.
Various tests were performed, including field-testing onboard a track geometry railcar operated by Norfolk Southern for evaluating the efficacy, accuracy, and durability of the LIDAR system; and laboratory tests on a 40-foot rail panel for assessing the ability to obtain measurements at super low speeds.
The test results indicate that when compared with other conventional means used by the railroad industry, LIDAR is capable of accurately measuring train speed and distance from speeds as slow as 0.3 mph and up to 100 mph. Additionally, the curvature
measurements proved to be as accurate as Inertial Measurement Units (IMUs) that are commonly used in track geometry measurement railcars.
Master of Science
Mallula, Christine. "Comparing Garmin Forerunner 405CX GPS and Nike + iPod to Accurately Measure Energy Expenditure, Distance, and Speed of Overground Running". Cleveland State University / OhioLINK, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=csu1273708884.
Texto completoHess, Marc Frederick. "Flight characteristics of pen-reared and wild prairie-chickens and an evaluation of a greenhouse to rear prairie-chickens". Thesis, Texas A&M University, 2003. http://hdl.handle.net/1969.1/163.
Texto completoTeixeira, Rogério Felipe Santos. "Distância, velocidade, proximidade e redes: fabricando conceitos em educação a distância". Universidade do Estado do Rio de Janeiro, 2008. http://www.bdtd.uerj.br/tde_busca/arquivo.php?codArquivo=5165.
Texto completoAt this work we present an investigation about some of the conditions that make possible the applications of the Distance Education in Brazil in order to discover the potential of this teaching/learning method that occur through the use of computers linked to the Internet. However, we choose to adopt an immanent perspective in research, which includes a multiplicity of issues that cross the Education as a whole, and not just its distance operation mode. We build some kind of historical cartography of the Distance Education practices in our country considering their political, economical, educational and, above all, ethical lines of constitution. We have reviewed some of the impacts on Distance Education in our country that are effect of the resentment that comes from the continuous and endless process of globalization, which affects different segments of our society, focusing in the teaching/learning contemporary practices. Facing this conjecture, we move forward, verifying how can we extract potencies of the weakness which are imposed to us by the neoliberal policies of nowadays. We work with the support of the studies of Deleuze and Foucault regarding to the movement that goes from the Societies of Discipline to the Societies of Control, mixed with the arrangements and alternatives proposed by the event of the Cognitive Capitalism. The conditions of experience and production of meaning(s) that are possible in Distance Education processes are investigated through the production of the concepts of distance, speed and proximity, when we assume the position between the two usual sides at Distance Education discussions that are composed in one part by enthusiasts and in other by its exagerated critics. We work still with some conceptualizations for the term network, considering it as a technique paraphernalia that enables computer connections, allowing the communication through the Internet, and also as a way of collectives mobilization that seek to multiply the meanings in their practices. We believe in the inherent capacity of the networks to considerably increase the power of action of the collectives involved in distance teaching/learning practices, through the implementation of strategies and micropolitical tactics, under the inspiration on the analysis about the process of the invention of everyday life practices presented in the work of Michel de Certeau.
Santos, Aline Robertina dos. "Curso a distância para professores: Conhecendo os segredos da voz e da expressividade". Universidade de São Paulo, 2012. http://www.teses.usp.br/teses/disponiveis/25/25143/tde-12062012-145921/.
Texto completoThe teacher needs to have a healthy voice, with good quality and good communicative performance for professional success. The use of the Internet can facilitate their access to such information. This study aimed to develop a distance learning course for teachers on health and vocal expressiveness that enables this population to take care of the voice and enhance communication in the classroom and bring satisfaction to the users. It was developed a site with theoretical content entitled \"Knowing the Secrets of Voice and Expressiveness\", which was made available to teachers in three modules: 1 - The voice and voice problems, 2 Vocal Health, and 3rd - The voice and oratory in the classroom. Actively participated in this study 10 teachers, 9 women and 1 man, aged between 25 and 54 years, belonging to public schools teaching elementary and high schools in the cities of Bauru, Suzano and Poa, the state of Sao Paulo. Participants completed questionnaires before and after the completion of the course which lasted a maximum of 30 days. To verify the knowledge and habits of the participants before and after the course, the results of the questionnaires were subjected to statistical analysis (t test - paired). After the course was administered a satisfaction questionnaire. There was an increase of knowledge, a reduction of negative habits and increase of positive habits, with statistical significance. With regard to user satisfaction, 80% considered the optimal course and 20% as good. The distance course \"Knowing the Secrets of Voice and Expressiveness\" was developed as proposed and shown to be a material that promoted the increase of knowledge and awareness about the harmful practices and appropriate use of voice and gave satisfaction to the teachers.
Stein, Andreas. "Test-retest reliability of Medicine Ball throws along with correlation to clubhead speed and carry distance in young skilled golfers". Thesis, Högskolan i Halmstad, Akademin för ekonomi, teknik och naturvetenskap, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-38106.
Texto completo