Global ETD Search

111	Integration of multiple feature sets for reducing ambiguity in automatic speech recognition MomayyezSiahkal, Parya. January 2008 (has links) This thesis presents a method to investigate the extent to which articulatory based acoustic features can be exploited to reduce ambiguity in automatic speech recognition search. The method proposed is based on a lattice re-scoring paradigm implemented to integrate articulatory based features into automatic speech recognition systems. Time delay neural networks are trained as feature detectors to generate feature streams over which hidden Markov models (HMMs) are defined. These articulatory based HMMs are combined with HMMs defined over spectral energy based Mel frequency cepstrum coefficient (MFCC) acoustic features through a sequential lattice re-scoring procedure. The optimum phone strings are found by maximizing the log-linear combination of acoustic and language models likelihoods during recognition. The associated log-linear weights are estimated using a discriminative model combination approach. All the experiments are performed using the DARPA TIMIT speech database and the results are presented in terms of phone accuracies. Automatic speech recognition. Hidden Markov models.
112	Experiments on automatic phonetic segmentation and transcription of speech Lennig, Matthew. January 1983 (has links) No description available. Speech processing systems. Automatic speech recognition.
113	Connectionist models applied to automatic speech recognition Bengio, Yoshua January 1987 (has links) No description available. Automatic speech recognition. NETL (Computer system) Perceptrons.
114	CLASS : a study of methods for coarse phonetic classification / Delmege, James W. January 1988 (has links) Thesis (M.S.)--Rochester Institute of Technology, 1988. / Includes appendixes. Includes bibliographical references (leaves 86-87).
115	Multi-signal processing for voice recognition in noisy environments / Nayfeh, Taysir H., January 1991 (has links) Thesis (M.S.)--Virginia Polytechnic Institute and State University, 1991. / Vita. Abstract. Includes bibliographical references (leaf 48). Also available via the Internet.
116	Discriminative training of stream weights in a multi-stream HMM as a linear programming problem / Ng, Yik Lun. January 2008 (has links) Thesis (M.Phil.)--Hong Kong University of Science and Technology, 2008. / Includes bibliographical references (leaves 48-53). Also available in electronic version.
117	A speech act model of air traffic control dialogue / Ward, Karen, January 1992 (has links) Thesis (M.S.)--Oregon Graduate Institute of Science and Technology, 1992.
118	Computer classification of stop consonants in a speaker independent continuous speech environment / Campanelli, Michael R. January 1991 (has links) Thesis (M.S.)--Rochester Institute of Technology, 1991. / Typescript. Includes bibliographical references.
119	Speaker recognition in reverberant environments / Gammal, Joseph, January 1900 (has links) Thesis (M. App. Sc.)--Carleton University, 2005. / Includes bibliographical references (p. 138-147). Also available in electronic format on the Internet.
120	Estimation of the number of syllables using hidden Markov models and design of a dysarthria classifier using global statistics of speech Mujumdar, Monali January 2006 (has links) Thesis (Ph. D.)--University of Wyoming, 2006. / Title from PDF title page (viewed on June 26, 2008). Includes bibliographical references (p. 140-143).

Search results