Zobrazeno 1 - 10
of 91
pro vyhledávání: '"J.-C. Junqua"'
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 8:695-707
This paper describes a new model-based speaker adaptation algorithm called the eigenvoice approach. The approach constrains the adapted model to be a linear combination of a small number of basis vectors obtained offline from a set of reference speak
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c8cdb56dbcd8600638d610ddbe90c22c
https://doi.org/10.1109/89.876308
https://doi.org/10.1109/89.876308
Publikováno v:
Hong Kong University of Science and Technology
The authors address the problem of automatic word boundary detection in quiet and in the presence of noise. Attention has been given to automatic word boundary detection for both additive noise and noise-induced changes in the talker's speech product
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7ec2237fbc8a5f9df57920bb80f325fb
https://doi.org/10.1109/89.294354
https://doi.org/10.1109/89.294354
Publikováno v:
Journal de Physique IV Proceedings
Journal de Physique IV Proceedings, EDP Sciences, 1994, 04 (C5), pp.C5-485-C5-488. ⟨10.1051/jp4:19945102⟩
Journal de Physique IV Proceedings, EDP Sciences, 1994, 04 (C5), pp.C5-485-C5-488. ⟨10.1051/jp4:19945102⟩
Le but de cette étude est de déterminer pour le français, au niveau phonétique, les différences acoustiques entre la parole normale et la parole prononcée en milieu bruité (soumise au réflexe Lombard). Ce travai1 fait suite à une première
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::800bacb4ab044107248bd87de23e2ef9
https://doi.org/10.1051/jp4:19945102
https://doi.org/10.1051/jp4:19945102
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 1:39-48
Several recently proposed automatic speech recognition (ASR) front-ends are experimentally compared in speaker-dependent, speaker-independent (or cross-speaker) recognition. The perceptually based linear predictive (PLP) front-end, with the root-powe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::30d1c844a9120de928a37729a031eb3b
https://doi.org/10.1109/89.221366
https://doi.org/10.1109/89.221366
Publikováno v:
IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..
HMM systems exhibit a large amount of redundancy. To this end, a technique called eigenvoices was found to be very effective for speaker adaptation. The correlation between HMM parameters is exploited via a linear constraint called eigenspace. This c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d0579813c3720e0f37cda9a5ae8b9de
https://doi.org/10.1109/asru.2001.1034591
https://doi.org/10.1109/asru.2001.1034591
Publikováno v:
ICASSP (2)
Speaker clustering is a key component in many speech processing applications. We focus on Broadcast News meta data annotation and speaker adaptation. In this setting, speaker clustering consists of identifying who spoke, and when they spoke in a long
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4390b9c2243bf93f5958d9c20b965c70
https://doi.org/10.1109/icassp.2003.1202300
https://doi.org/10.1109/icassp.2003.1202300
Autor:
J.-C. Junqua, H. Wakita
Publikováno v:
Proceedings. Electrotechnical Conference Integrating Research, Industry and Education in Energy and Communication Engineering'.
The authors describe a novel automatic segmentation system based on perceptual cues, spectral dynamics, and various sources of knowledge: heuristic, phonetic, and suprasegmental. Because no reference units are used, the method can be directly applied
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::32078d7f4d55ea5bdf172fa5cf06b85c
https://doi.org/10.1109/melcon.1989.50026
https://doi.org/10.1109/melcon.1989.50026
A comparative study of cepstral lifters and distance measures for all pole models of speech in noise
Autor:
J.-C. Junqua, H. Wakita
Publikováno v:
ICASSP
After a brief overview of the techniques utilized, the authors evaluate perceptually based linear prediction (PLP) analysis, and then report the results of a comparative study of several front-ends in the case of speech produced in quiet and noisy en
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7ecbb63751aa44ae2653c1ae795f5453
https://doi.org/10.1109/icassp.1989.266467
https://doi.org/10.1109/icassp.1989.266467
Autor:
L. Vassallo, J.-C. Junqua
Publikováno v:
ICSLP
Reports on the performance of two variants of well-known statistical-based clustering techniques and presents an evaluation on the TIMIT and TI-Digit databases. A clustering approach which (1) is based on a divergence criterion, (2) separates "good"
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::744abd9de67f28ab019c9e3083755d15
https://doi.org/10.1109/icslp.1996.607257
https://doi.org/10.1109/icslp.1996.607257
Publikováno v:
ICASSP
In the field of speech recognition by stochastic methods, it is conventional to pursue approaches using first-order-hidden Markov models (HMM1s). Despite the success of this approach, it is still worth investigating if some of the drawbacks of HMM1s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5eb710a61377643bbf18417b3f172edf
https://doi.org/10.1109/icassp.1996.541126
https://doi.org/10.1109/icassp.1996.541126