Zobrazeno 1 - 10
of 44
pro vyhledávání: '"G. Zavaliagkos"'
Publikováno v:
Speech Communication. 31:51-67
According to discourse theories in linguistics, conversational utterances possess an informational structure. That is, each sentence consists of two components: the given and the new . The given refers to information that has previously been conveyed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7c1a2a748bc4db24902431d53b35ddd2
https://doi.org/10.1016/s0167-6393(99)00060-6
https://doi.org/10.1016/s0167-6393(99)00060-6
Autor:
Murat Saraclar, Michael Finke, William Byrne, John McDonough, Sanjeev Khudanpur, G. Zavaliagkos, Michael Riley, Chuck Wooters, Harriet J. Nock, Andrej Ljolje
Publikováno v:
Speech Communication. 29:209-224
In the early 1990s, the availability of the TIMIT read-speech phonetically transcribed corpus led to work at AT&T on the automatic inference of pronunciation variation. This work, briefly summarized here, used stochastic decision trees trained on pho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1cf1edcc778a4459cfc39061e2986b5e
https://doi.org/10.1016/s0167-6393(99)00037-0
https://doi.org/10.1016/s0167-6393(99)00037-0
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 2:151-160
The current state-of-the-art in large-vocabulary, continuous speech recognition is based on the use of hidden Markov models (HMM). In an attempt to improve over HMM performance, the authors developed a hybrid system that combines the advantages of ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ae6b3cb9dd6f147b220eaae396e0c5cb
https://doi.org/10.1109/89.260358
https://doi.org/10.1109/89.260358
Publikováno v:
International Journal of Pattern Recognition and Artificial Intelligence. :949-963
Up till recently, state-of-the-art, large vocabulary, continuous speech recognition (CSR) had employed hidden Markov modeling (HMM) to model speech sounds. In an attempt to improve over HMM we developed a hybrid system that integrates HMM technology
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e66905dadba5d25aba5cb530f4d02d2
https://doi.org/10.1142/s0218001493000480
https://doi.org/10.1142/s0218001493000480
Publikováno v:
ICASSP
We present a framework for maximum a posteriori (MAP) adaptation of large scale HMM recognizers. First we review the standard MAP adaptation for Gaussian mixtures. We then show how MAP can be used to estimated transformations which are shared across
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7aab1c5b008703905007ff0db196514d
https://doi.org/10.1109/icassp.1996.543223
https://doi.org/10.1109/icassp.1996.543223
Publikováno v:
ICASSP
We formulate a novel approach to speaker adaptation. It is predicated upon the fact that the cepstral coefficients used as feature vectors in most state of the art speech recognition systems are coefficients of a Laurent series, and hence represent a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cdbdaa495696d0031bae69cbba277bda
https://doi.org/10.1109/icassp.1996.543222
https://doi.org/10.1109/icassp.1996.543222
Autor:
Richard Schwartz, Francis Kubala, G. Zavaliagkos, John Makhoul, Long Nguyen, Tasos Anastasakos
Publikováno v:
ICASSP (1)
HLT
HLT
We describe recent changes to the BYBLOS system's training and recognition algorithms and report on numerous experiments in large vocabulary speech recognition. In earlier work, we performed five key experiments that were designed to answer questions
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eeebad6fc615bd8de602c587fc24dab9
https://doi.org/10.1109/icassp.1994.389232
https://doi.org/10.1109/icassp.1994.389232
Publikováno v:
ICASSP
According to discourse theories in linguistics, conversational utterances possess an informational structure that partitions each sentence into two portions: a "given" and "new". We explore this idea by building sub-sentence discourse language models
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3f0ce1a7e665eaaf90248c3f750485cc
https://doi.org/10.1109/icassp.1998.675359
https://doi.org/10.1109/icassp.1998.675359
Autor:
Fred Richardson, A. El-Jaroudi, G. Zavaliagkos, J. McDonough, Jayadev Billa, Kristine W. Ma, Herbert Gish, D. Miller, Man-Hung Siu
Publikováno v:
ICASSP
This paper presents the 1997 BBN Byblos large vocabulary speech recognition (LVCSR) system. We give an outline of the algorithms and procedures used to train the system, describe the recognizer configuration and present the major technological innova
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c68a34416e690cbd090944a0571e89b
https://doi.org/10.1109/icassp.1998.675412
https://doi.org/10.1109/icassp.1998.675412
Autor:
Michael Finke, William Byrne, Murat Saraclar, G. Zavaliagkos, Chuck Wooters, S. Khunanpur, Harriet J. Nock, Michael Riley, John McDonough
Publikováno v:
ICASSP
Accurately modelling pronunciation variability in conversational speech is an important component of an automatic speech recognition system. We describe some of the projects undertaken in this direction during and after WS97, the Fifth LVCSR Summer W
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3b0c11768328a17f6a9d881b563b7536
https://doi.org/10.1109/icassp.1998.674430
https://doi.org/10.1109/icassp.1998.674430