Sciweavers

9521 search results - page 1558 / 1905
» Compiling with continuations, continued
Sort
View
ICASSP
2011
IEEE
14 years 10 months ago
Optimum multi-user detection by nonsmooth optimization
—The optimum multiuser detection (OMD) is a discrete (binary) optimization. The previously developed approaches often relax it by a semi-definite program (SDP) and then employ r...
Hoang Duong Tuan, Tran Thai Son, Hoang Tuy, Ha H. ...
ICASSP
2011
IEEE
14 years 10 months ago
Machine and acoustical condition dependency analyses for fast acoustic likelihood calculation techniques
The acceleration of acoustic likelihood calculation has been an important research issue for developing practical speech recognition systems. And there are various specification ...
Atsunori Ogawa, Satoshi Takahashi, Atsushi Nakamur...
ICASSP
2011
IEEE
14 years 10 months ago
The MIT LL 2010 speaker recognition evaluation system: Scalable language-independent speaker recognition
Research in the speaker recognition community has continued to address methods of mitigating variational nuisances. Telephone and auxiliary-microphone recorded speech emphasize th...
Douglas E. Sturim, William M. Campbell, Najim Deha...
ICASSP
2011
IEEE
14 years 10 months ago
Efficient search of music pitch contours using wavelet transforms and segmented dynamic time warping
We propose a method of music melody matching based on their “continuous” (or “time-frame-based”) pitch contours. Most previous methods using frame-based contours either ma...
Woojay Jeon, Changxue Ma
ICASSP
2011
IEEE
14 years 10 months ago
Structured Output Layer neural network language model
This paper introduces a new neural network language model (NNLM) based on word clustering to structure the output vocabulary: Structured Output Layer NNLM. This model is able to h...
Hai Son Le, Ilya Oparin, Alexandre Allauzen, Jean-...
« Prev « First page 1558 / 1905 Last » Next »