International Conference on Acoustics, Speech, and Signal Processing · 2002 · 26 citations · 5 references
Language StudiesLinguisticsNatural Language ProcessingPhoneticsPhonologyHidden Markov ModelsLanguage ModelingPhonological AnalysisSpeech AcousticsSpeech RecognitionSpeech Recognition TestingAccuracy In Word IdentificationPronunciation AccuracyPronunciation ModelingSpeaker AdaptationSpeaker-dependent Speech RecognitionSpeaker-independent Speech RecognitionSpeech Recognition AcousticsWord Recognition Accuracy
A large-vocabulary, continuous-speech system, called DECIPHER, which is based on a hidden Markov model (HMM) approach and is designed to achieve high word accuracy in a speaker-independent mode is described. The results of a series of experiments that test acoustic and phonological adaptation of the DECIPHER system to the pronunciations of a single speaker in a speaker-dependent task are presented. Estimating the probabilities of alternative pronunciations and speaker-dependent phonology are discussed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
5
The DARPA 1000-word resource management database for continuous speech recognition
P. Price, William M. Fisher, Jacob Bernstein et al. · 2003 · 341 citations
BYBLOS: The BBN continuous speech recognition system
Y.-L. Chow, M. Dunham, Owen Kimball et al. · 2005 · 161 citations
Phonological structures for speech recognition
Michael H. Cohen, Lotfi A. Zadeh · 1989 · 65 citations
Language Studies, Linguistics, Computational Linguistics +13