Fast speaker adaptation: some experiments on different techniques for codebook and HMM parameters estimation
Published 1 January 1991
Marco Ferretti, Antonio Mazza
Citations4
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A set of techniques to perform fast speaker adaptation for a large vocabulary, natural-language, speech recognition system are presented and the experimentation has been carried out using a 20000-word, real-time,natural-language speech recognizer for the Italian language.
Abstract
A set of techniques to perform fast speaker adaptation for a large vocabulary, natural-language, speech recognition system are presented. The experimentation has been carried out using a 20000-word, real-time, natural-language speech recognizer for the Italian language. To perform speaker adaptation within the framework of the probabilistic approach to speech recognition two different problems must be addressed: codebook adaptation and hidden Markov model parameters adaptation. The basic idea is to use a set of data collected from several different speakers as a source of a priori knowledge with a small speech sample provided by the new speaker to perform the adaptation task. Several different techniques for codebook adaptation have been tried and discussed.>
Keywords
Computer Science
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Maximum Likelihood Approach to Continuous Speech Recognition
1,220 Citations1983L.R. Bahl, Frederick Jelinek +1 more
This paper describes a number of statistical models for use in speech recognition, with special attention to determining the parameters for such models from sparse data, and describes two decoding methods appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks.
Informatik-FachberichteThe Development of an Experimental Discrete Dictation Recognizer
176 Citations1986Frederick Jelinek
The paper outlines the self-organized, statistical approach underlying the basic algorithms of the recognizer, and considers important issues in the future development of dictation recognizers, such as vocabulary selection, language model creation, and human factors.
Proceedings of the IEEEThe development of an experimental discrete dictation recognizer
153 Citations1985F. Jelinek
Speaker adaptation through vector quantization
96 Citations2005Kiyohiro Shikano, Kai-Fu Lee +1 more
Vector quantization (VQ) is a technique that reduces the computation amount and memory size drastically and is proposed in order to improve speaker-independent recognition.
International Conference on Acoustics, Speech, and Signal ProcessingImproved speaker adaptation using text dependent spectral mappings.
32 Citations1988Ming-Whei Feng, Francis Kubala +2 more
A new probabdistic spectral edure is investigated to estimate the transformation of speaker adaptation and it is found that significant unprovement in recognition has been achieved compared to the previous adaptation algorithm.
Improved speaker adaption using text dependent spectral mappings
25 Citations2003M.-W. Feng, F. Kubla +2 more
A novel text-dependent probabilistic spectral mapping method is presented for rapid speaker adaptation that results in significant better performance than the previous algorithms, and also provides recognition performance which is less than two times the word error rate for speaker-dependent training.
International Conference on Acoustics, Speech, and Signal ProcessingA comparative study of spectral mapping for speaker adaptation
24 Citations2002Satoshi Nakamura, Kiyohiro Shikano
An investigation of the actual spectrogram shows that the fuzzy VQ-based spectral mapping works better than the neural network mapping, which is about 6% better in spectral distortion than nonlinear spectral mapping by a feedforward neural network.
Phoneme classification for real time speech recognition of Italian
22 Citations2005P. D'Orta, Marco Ferretti +1 more
This work investigates methods based on the definition of a similarity measure of Hidden Markov Models of phonemes, and on the automatic identification of broad phonetic classes via clustering algorithms, that create classes of equivalence among words by means of a phoneme classification.
International Conference on Acoustics, Speech, and Signal ProcessingSpeaker adaptation from a speaker-independent training corpus
21 Citations2002Francis Kubala, Richard Schwartz +1 more
A technique for using the speech of multiple reference speakers as a basis for speaker adaptation in large-vocabulary continuous-speech recognition is introduced, and the usual probabilistic spectrum transformation can be applied to the reference HMM to model a new speaker.
International Conference on Acoustics, Speech, and Signal ProcessingSpeaker adaptation for large vocabulary speech recognition systems using speaker Markov models
19 Citations1989Gerhard Rigoll
An alternative approach to speaker adaptation for a large-vocabulary hidden-Markov-model-based speech recognition system is described, based on the use of a stochastic model representing the different properties of the new speaker and an old speaker for which the full training set of 20 minutes is available.
Speaker adaptation method for HMM-based speech recognition
17 Citations2003Masafumi Nishimura, Kohei Sugawara
The authors describe a speaker adaptation method consisting of two stages, in the first stage, label prototypes, which represent spectral features, are modified to reduce the total distortion error of vector quantization for a new speaker.
IBM Journal of Research and DevelopmentLarge-vocabulary speech recognition: A system for the Italian language
14 Citations1988P. D'Orta, Marco Ferretti +4 more
A research project in automatic speech recognition is described which has led to the development of an experimental large-vocabulary real-time recognizer for Italian, and how the maximum-likelihood techniques which had been employed in theDevelopment of prototype recognizers for English can be tailored to a language with substantially different characteristics.
Unsupervised adaptation to new speakers in feature-based letter recognition
4 Citations2005Moshé J. Lasry, Richard M. Stern
Two new methods by which the CMU feature-based recognition system can learn the acoustical characteristics of individual speakers without feedback from the user are described.
IEEE Transactions on Acoustics Speech and Signal ProcessingSpeaker-dependent isolated word recognition using speaker-independent vector quantization codebooks augmented with speaker-specific data
4 Citations1985D. Burton, John E. Shore
A hybrid approach to speaker-dependent isolated word recognition that merges speaker-specific information obtained from a single training utterance with multisection vector quantization codebooks that were designed for speaker-independent recognition is discussed.