Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Christophe Ris"'
Autor:
Christophe Ris, D. Jouvet, Richard Rose, R. De Mori, Mohamed Faouzi BenZeghiba, Pietro Laface, Christian Wellekens, Olivier Deroo, Vivek Tyagi, Stéphane Dupont, T. Erbes, Luciano Fissore, Alfred Mertins
Publikováno v:
Speech Communication
Speech Communication, Elsevier : North-Holland, 2007, ⟨10.1016/j.specom.2007.02.006⟩
Speech Communication, Elsevier : North-Holland, 2007, ⟨10.1016/j.specom.2007.02.006⟩
International audience; Major progress is being recorded regularly on both the technology and exploitation of automatic speech recognition (ASR) and spoken language systems. However, there are still technological barriers to flexible solutions and us
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3db5655a526c4e20c54e88be24978efa
https://doi.org/10.1016/j.specom.2007.02.006
https://doi.org/10.1016/j.specom.2007.02.006
Autor:
Christophe Ris, Erhan Mengusoglu
Publikováno v:
Acoustics Research Letters Online. 6:92-98
In this paper, a new acoustic confidence measure of automatic speech recognition hypothesis is proposed and it is compared to approaches proposed in the literature. This approach takes into account prior information on the acoustic model performance
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d48ba9ec3b3b0f8192632e8884b36f10
https://doi.org/10.1121/1.1843171
https://doi.org/10.1121/1.1843171
Publikováno v:
Speech Communication. 40:503-515
In this paper we compare two different methods for automatically phonetically labeling a continuous speech data-base, as usually required for designing a speech recognition or speech synthesis system. The first method is based on temporal alignment o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c9dc0806e68deeba996f84a9285a59b
https://doi.org/10.1016/s0167-6393(02)00131-0
https://doi.org/10.1016/s0167-6393(02)00131-0
Autor:
Stéphane Dupont, Christophe Ris
Publikováno v:
Speech Communication. 34:141-158
In this paper, we assess and compare four methods for the local estimation of noise spectra, namely the energy clustering, the Hirsch histograms, the weighted average method and the low-energy envelope tracking. Moreover we introduce, for these four
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::92e028ee0ed7944bb120568d263070a5
https://doi.org/10.1016/s0167-6393(00)00051-0
https://doi.org/10.1016/s0167-6393(00)00051-0
Publikováno v:
IEEE Workshop on Automatic Speech Recognition and Understanding, 2005..
The paper proposes a solution that brings some advances to the genericity of the ASR technology towards tasks and languages. A non-linear discriminant model is built from multi-lingual, multi-task speech material in order to classify the acoustic sig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c528a47c38c7c468b33e52990d62f6c6
https://doi.org/10.1109/asru.2005.1566527
https://doi.org/10.1109/asru.2005.1566527
Publikováno v:
ICASSP
This paper presents a new algorithm of supervised vector quantization based on codebook mapping and maximization of mutual information. Classical VQ algorithms are usually based on minimization of a distortion criterion and hence, the phonetic classi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::54b462bfc30ce280ab00b28f8f1c5272
https://doi.org/10.1109/icassp.1996.543190
https://doi.org/10.1109/icassp.1996.543190
Publikováno v:
ICASSP
We present and compare two different hybrid HMM/MLP approaches. The first one uses MLPs as labelers coupled with a discrete HMM while the second one takes advantage of the ability of MLPs trained as classifiers to estimate a posteriori probabilities.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e90a327ea47e68b98343843de34dea19
https://doi.org/10.1109/icassp.1996.550598
https://doi.org/10.1109/icassp.1996.550598
Publikováno v:
ICASSP
This paper presents a new pre-processing method developed with the objective to represent relevant information of a signal with a minimum number of parameters. The originality of this work is to propose a new efficient pre-processing algorithm produc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f86bba18e69d114dc76c57fc21dacb7e
https://doi.org/10.1109/icassp.1995.479603
https://doi.org/10.1109/icassp.1995.479603
Autor:
Laurent Couvreur, Christophe Ris
Publikováno v:
7th International Conference on Spoken Language Processing (ICSLP 2002).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7924f6950fc3e5d2587e0a5f07144bbd
https://doi.org/10.21437/icslp.2002-597
https://doi.org/10.21437/icslp.2002-597
Autor:
Erhan Mengusoglu, Christophe Ris
Publikováno v:
7th European Conference on Speech Communication and Technology (Eurospeech 2001).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4873fdc2d75ebc18be33f03a9e7a11a4
https://doi.org/10.21437/eurospeech.2001-598
https://doi.org/10.21437/eurospeech.2001-598