—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. ...
The acceleration of acoustic likelihood calculation has been an important research issue for developing practical speech recognition systems. And there are various specification ...
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...
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...
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-...