Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Vassilios Digalakis"'
Publikováno v:
IEEE Transactions on Audio, Speech and Language Processing. 15:928-938
The porting of a speech recognition system to a new language is usually a time-consuming and expensive process since it requires collecting, transcribing, and processing a large amount of language-specific training sentences. This work presents techn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::708aa91eeb2ca71ff8c9c6102db2e1f0
https://doi.org/10.1109/tasl.2006.885259
https://doi.org/10.1109/tasl.2006.885259
Autor:
Vassilios Digalakis, N. Moustroufas
Publikováno v:
Computer Speech & Language. 21:219-230
In this study we present various techniques to evaluate the pronunciation of students of a foreign language without any knowledge of the uttered text. Previous attempts have shown that it is feasible to evaluate the pronunciation of a non-native spea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::156031acdb947c1785b19d8de6b04161
https://doi.org/10.1016/j.csl.2006.04.001
https://doi.org/10.1016/j.csl.2006.04.001
Publikováno v:
MLSP
Gaussian graphical models are of great interest in statistical learning. Since the conditional independence between the variables corresponds to zero entries in the inverse covariance matrix, one can learn the structure of the graph by estimating a s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::37e4fa886d8303e35f7c8e8004fcb154
https://doi.org/10.1109/mlsp.2014.6958915
https://doi.org/10.1109/mlsp.2014.6958915
Publikováno v:
Computer Speech & Language. 15:257-285
Speaker adaptation is recognized as an essential part of today?s large-vocabulary automatic speech recognition systems. A family of techniques that has been extensively applied for limited adaptation data is transformation-based adaptation. In transf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c30dd35eda4d79a3d7aeae4a1ed2f106
https://doi.org/10.1006/csla.2001.0168
https://doi.org/10.1006/csla.2001.0168
Publikováno v:
Computer Speech & Language. 14:33-46
This paper introduces a new form of observation distributions for hidden Markov models (HMMs), combining subvector quantization and mixtures of discrete distributions. Despite what is generally believed, we show that discrete-distribution HMMs can ou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da53336f637028869d0e54d02fbb3f51
https://doi.org/10.1006/csla.1999.0134
https://doi.org/10.1006/csla.1999.0134
Autor:
Vassilios Digalakis
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 7:253-261
The mismatch that frequently occurs between the training and testing conditions of an automatic speech recognizer can be efficiently reduced by adapting the parameters of the recognizer to the testing conditions. Two measures that characterize the pe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0895d7d88a4abc35f5f25a056dbd6bc9
https://doi.org/10.1109/89.759031
https://doi.org/10.1109/89.759031
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 7:177-187
The recognition accuracy in previous large vocabulary automatic speech recognition (ASR) systems is highly related to the existing mismatch between the training and testing sets. For example, dialect differences across the training and testing speake
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7757fce5f615f284a3b3ee3866663d7e
https://doi.org/10.1109/89.748122
https://doi.org/10.1109/89.748122
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 4:281-289
Summarization: An algorithm is proposed that achieves a good tradeoff between modeling resolution and robustness by using a new, general scheme for tying of mixture components in continuous mixture-density hidden Markov model (HMM)-based speech recog
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::257076953ed66c3b51fbf51e78718a08
https://doi.org/10.1109/89.506931
https://doi.org/10.1109/89.506931
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 4:360-378
Many alternative models have been proposed to address some of the shortcomings of the hidden Markov model (HMM), which is currently the most popular approach to speech recognition. In particular, a variety of models that could be broadly classified a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d934ac107600deb08ea223c62027e21b
https://doi.org/10.1109/89.536930
https://doi.org/10.1109/89.536930
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 3:357-366
A trend in automatic speech recognition systems is the use of continuous mixture-density hidden Markov models (HMMs). Despite the good recognition performance that these systems achieve on average in large vocabulary applications, there is a large va
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::258635de44f67ec065d87bdbe153da4c
https://doi.org/10.1109/89.466659
https://doi.org/10.1109/89.466659