Sciweavers

246 search results - page 44 / 50
» interspeech 2010
Sort
View
INTERSPEECH
2010
14 years 5 months ago
Audio-visual anticipatory coarticulation modeling by human and machine
The phenomenon of anticipatory coarticulation provides a basis for the observed asynchrony between the acoustic and visual onsets of phones in certain linguistic contexts. This ty...
Louis H. Terry, Karen Livescu, Janet B. Pierrehumb...
INTERSPEECH
2010
14 years 5 months ago
Text-based unstressed syllable prediction in Mandarin
Recently, an increasing attention has been paid to Mandarin word stress which is important for improving the naturalness of speech synthesis. Most of the research on Mandarin spee...
Ya Li, Jianhua Tao, Meng Zhang, Shifeng Pan, Xiaoy...
INTERSPEECH
2010
14 years 5 months ago
On the relation of Bayes risk, word error, and word posteriors in ASR
In automatic speech recognition, we are faced with a wellknown inconsistency: Bayes decision rule is usually used to minimize sentence (word sequence) error, whereas in practice w...
Ralf Schlüter, Markus Nußbaum-Thom, Her...
INTERSPEECH
2010
14 years 5 months ago
Recurrent neural network based language model
A new recurrent neural network based language model (RNN LM) with applications to speech recognition is presented. Results indicate that it is possible to obtain around 50% reduct...
Tomas Mikolov, Martin Karafiát, Lukas Burge...
INTERSPEECH
2010
14 years 5 months ago
Dialect recognition using a phone-GMM-supervector-based SVM kernel
In this paper, we introduce a new approach to dialect recognition which relies on the hypothesis that certain phones are realized differently across dialects. Given a speaker'...
Fadi Biadsy, Julia Hirschberg, Michael Collins