A review of large-vocabulary continuous-speech
S Young - IEEE signal processing magazine, 1996 - ieeexplore.ieee.org
Considerable progress has been made in speech-recognition technology over the last few
years and nowhere has this progress been more evident than in the area of large …
years and nowhere has this progress been more evident than in the area of large …
[PDF][PDF] Speaker adaptation for continuous density HMMs: A review
PC Woodland - ISCA Tutorial and Research Workshop (ITRW) on …, 2001 - Citeseer
This paper reviews some popular speaker adaptation schemes that can be applied to
continuous density hidden Markov models. These fall into three families based on MAP …
continuous density hidden Markov models. These fall into three families based on MAP …
[图书][B] Digital speech processing: synthesis, and recognition
S Furui - 2018 - taylorfrancis.com
A study of digital speech processing, synthesis and recognition. This second edition
contains new sections on the international standardization of robust and flexible speech …
contains new sections on the international standardization of robust and flexible speech …
Rapid speaker adaptation in eigenvoice space
This paper describes a new model-based speaker adaptation algorithm called the
eigenvoice approach. The approach constrains the adapted model to be a linear …
eigenvoice approach. The approach constrains the adapted model to be a linear …
Structure in talker-specific phonetic realization: Covariation of stop consonant VOT in American English
E Chodroff, C Wilson - Journal of Phonetics, 2017 - Elsevier
Variation across talkers in the acoustic-phonetic realization of speech sounds is a pervasive
property of spoken language. The present study provides evidence that variation across …
property of spoken language. The present study provides evidence that variation across …
[图书][B] Handbook of neural computation
E Fiesler, R Beale - 2020 - books.google.com
The Handbook of Neural Computation is a practical, hands-on guide to the design and
implementation of neural networks used by scientists and engineers to tackle difficult and/or …
implementation of neural networks used by scientists and engineers to tackle difficult and/or …
[PDF][PDF] Eigenvoices for speaker adaptation
We have devised a new class of fast adaptation techniques for speech recognition, based
on prior knowledge of speaker variation. To obtain this prior knowledge, one applies …
on prior knowledge of speaker variation. To obtain this prior knowledge, one applies …
On adaptive decision rules and decision parameter adaptation for automatic speech recognition
CH Lee, Q Huo - Proceedings of the IEEE, 2000 - ieeexplore.ieee.org
Recent advances in automatic speech recognition are accomplished by designing a plug-in
maximum a posteriori decision rule such that the forms of the acoustic and language model …
maximum a posteriori decision rule such that the forms of the acoustic and language model …
On stochastic feature and model compensation approaches to robust speech recognition
CH Lee - Speech Communication, 1998 - Elsevier
By now it should not be surprising that high performance speech recognition systems can be
designed for a wide variety of tasks in many different languages. This is mainly attributed to …
designed for a wide variety of tasks in many different languages. This is mainly attributed to …
Combined Bayesian and predictive techniques for rapid speaker adaptation of continuous density hidden Markov models
SM Ahadi, PC Woodland - Computer speech & language, 1997 - Elsevier
One problem faced by some model adaptation techniques is that only the parameters of
those models which are observed in the adaptation data are updated. Hence, with small …
those models which are observed in the adaptation data are updated. Hence, with small …