Sciweavers

679 search results - page 102 / 136
» speech 2010
Sort
View
INTERSPEECH
2010
14 years 6 months ago
Can tongue be recovered from face? the answer of data-driven statistical models
This study revisits the face-to-tongue articulatory inversion problem in speech. We compare the Multi Linear Regression method (MLR) with two more sophisticated methods based on H...
Atef Ben Youssef, Pierre Badin, Gérard Bail...
INTERSPEECH
2010
14 years 6 months ago
Regularized-MLLR speaker adaptation for computer-assisted language learning system
In this paper, we propose a novel speaker adaptation technique, regularized-MLLR, for Computer Assisted Language Learning (CALL) systems. This method uses a linear combination of ...
Dean Luo, Yu Qiao, Nobuaki Minematsu, Yutaka Yamau...
INTERSPEECH
2010
14 years 6 months ago
Channel detectors for system fusion in the context of NIST LRE 2009
One of the difficulties in Language Recognition is the variability of the speech signal due to speakers and channels. If channel mismatch is too big and when different categories ...
Florian Verdet, Driss Matrouf, Jean-Françoi...
INTERSPEECH
2010
14 years 6 months ago
Prominence detection in Swedish using syllable correlates
This paper presents an approach to estimating word level prominence in Swedish using syllable level features. The paper discusses the mismatch problem of annotations between word ...
Samer Al Moubayed, Jonas Beskow
INTERSPEECH
2010
14 years 6 months ago
Domain adaptation and compensation for emotion detection
Inspired by the recent improvements in domain adaptation and session variability compensation techniques used for speech and speaker processing, we study their effect for emotion ...
Michelle Hewlett Sanchez, Gökhan Tür, Lu...