683 search results - page 109 / 137 » speech 2008 |
128
click to vote
ICASSP
2008
IEEE
15 years 10 months ago
2008
IEEE
In this paper, an efficient method for language model lookahead probability generation is presented. Traditional methods generate language model look-ahead (LMLA) probabilities fo...
121
click to vote
DEXAW
2008
IEEE
15 years 10 months ago
2008
IEEE
Content based search in audio-visual collections requires media specific analysis for extracting low level features to be efficiently indexed and searched. We present the SAPIR ...
117
click to vote
ICASSP
2009
IEEE
15 years 10 months ago
2009
IEEE
We describe a new GMM-UBM speaker recognition system that uses standard cepstral features, but selects different frames of speech for different subsystems. Subsystems, or “const...
ICASSP
2008
IEEE
15 years 10 months ago
2008
IEEE
Recently the concept of ideal binary time-frequency masks has received attention and their optimality in terms of signalto-noise ratio has been presumed. However the optimality is...
115
click to vote
ICASSP
2008
IEEE
15 years 10 months ago
2008
IEEE
Equalization techniques for room impulse responses (RIRs) are important in acoustic signal processing applications such as speech dereverberation. In practice, only approximate es...