Sciweavers

34 search results - page 4 / 7
» Non-linear noise compensation for robust speech recognition ...
Sort
View
ICASSP
2008
IEEE
14 years 12 days ago
Cepstral domain feature compensation based on diagonal approximation
In this paper, we propose a novel approach to feature compensation performed in the cepstral domain. We apply the linear approximation method in the cepstral domain to simplify th...
Woohyung Lim, Chang Woo Han, Jong Won Shin, Nam So...
SPEECH
2010
136views more  SPEECH 2010»
13 years 4 months ago
Robust speech recognition by integrating speech separation and hypothesis testing
Missing data methods attempt to improve robust speech recognition by distinguishing between reliable and unreliable data in the time-frequency domain. Such methods require a binar...
Soundararajan Srinivasan, DeLiang L. Wang
CSL
2007
Springer
13 years 6 months ago
On noise masking for automatic missing data speech recognition: A survey and discussion
Automatic speech recognition (ASR) has reached very high levels of performance in controlled situations. However, the performance degrades significantly when environmental noise ...
Christophe Cerisara, Sébastien Demange, Jea...
NIPS
2001
13 years 7 months ago
Speech Recognition with Missing Data using Recurrent Neural Nets
In the `missing data' approach to improving the robustness of automatic speech recognition to added noise, an initial process identifies spectraltemporal regions which are do...
S. Parveen, P. Green
TASLP
2008
133views more  TASLP 2008»
13 years 4 months ago
Minimum Mean-Squared Error Estimation of Mel-Frequency Cepstral Coefficients Using a Novel Distortion Model
In this paper, a new method for statistical estimation of Mel-frequency cepstral coefficients (MFCCs) in noisy speech signals is proposed. Previous research has shown that model-ba...
Kevin M. Indrebo, Richard J. Povinelli, Michael T....