1992 · 56 citations · 7 references
ComputingComputer ScienceMachine LearningNatural Language ProcessingStatistical LearningHidden Markov ModelsPattern RecognitionSpeech AcousticsSpeech RecognitionFeedforward Neural NetworksHidden Markov Model TrainingProbability EstimationSpeaker-independent Speech RecognitionSpeech Understanding
The authors have previously demonstrated that feedforward networks can be used to estimate local output probabilities in hidden Markov model (HMM) speech recognition systems (Renals et al., 1991). These connectionist techniques are integrated into the DECIPHER system, with experiments being performed using the speaker-independent DARPA RM database. The results indicate that: connectionist probability estimation can improve performance of a context-independent maximum-likelihood-trained HMM system; performance of the connectionist system is close to what can be achieved using (context-dependent) HMM systems of much higher complexity; and mixing connectionist and maximum-likelihood estimates can improve the performance of the state-of-the-art context-independent HMM system.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
7
A Stochastic Approximation Method
Herbert Robbins, Sutton Monro · The Annals of Mathematical Statistics · 1951 · 9.6K citations · Full text
Phonological structures for speech recognition
Michael H. Cohen, Lotfi A. Zadeh · 1989 · 65 citations
Language Studies, Linguistics, Computational Linguistics +13
Continuous speech recognition using PLP analysis with multilayer perceptrons
N. Morgan, Hynek Heřmanský, H. Bourlard et al. · 1991 · 28 citations