Sciweavers

4985 search results - page 187 / 997
» Observation of String-Rewriting Systems
Sort
View
108
Voted
ICASSP
2011
IEEE
14 years 7 months ago
Multi-class Model M
Model M, a novel class-based exponential language model, has been shown to significantly outperform word n-gram models in state-of-the-art machine translation and speech recognit...
Ahmad Emami, Stanley F. Chen
131
Voted
ICASSP
2011
IEEE
14 years 7 months ago
Multichannel nonnegative tensor factorization with structured constraints for user-guided audio source separation
Separating multiple tracks from professionally produced music recordings (PPMRs) is still a challenging problem. We address this task with a user-guided approach in which the sepa...
Alexey Ozerov, Cédric Févotte, Rapha...
122
Voted
ICASSP
2011
IEEE
14 years 7 months ago
Preserve ordering property of generated LSPS for minimum generation error training in HMM-based speech synthesis
Ordering property is an important property of LSP and closely connected with the naturalness of reconstructed speech. When LSP is adopted as spectrum feature in HMM-based parametr...
Ming Lei, Zhen-Hua Ling, Li-Rong Dai
ICASSP
2011
IEEE
14 years 7 months ago
Efficiently computing private recommendations
Online recommender systems enable personalized service to users. The underlying collaborative filtering techniques operate on privacy sensitive user data, which could be misused ...
Zekeriya Erkin, M. Beye, T. Veugen, Reginald L. La...
111
Voted
ICASSP
2011
IEEE
14 years 7 months ago
Spectral magnitude minimum mean-square error binary masks for DFT based speech enhancement
Originally, ideal binary mask (idbm) techniques have been used as a tool for studying aspects of the auditory system. More recently, idbm techniques have been adapted to the pract...
Jesper Jensen, Richard C. Hendriks