135 search results - page 4 / 27 » Temporal Feature Selection for Noisy Speech Recognition |
165
click to vote
INTERSPEECH
2010
15 years 1 months ago
2010
The Lombard effect refers to the speech changes due to the immersion of the speaker in a noisy environment. Among these changes, studies have already reported acoustic modificatio...
203
click to vote
TASLP
2011
15 years 1 months ago
2011
— Missing feature theory (MFT) has demonstrated great potential for improving the noise robustness in speech recognition. MFT was mostly applied in the log-spectral domain since ...
177
click to vote
ICMCS
2005
IEEE
16 years 6 days ago
2005
IEEE
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...
200
click to vote
IJCNN
2000
IEEE
15 years 10 months ago
2000
IEEE
This paper presents an unsupervised segmentation method for feature sequences based on competitivelearning hidden Markov models. Models associated with the nodes of the Self-Organ...
181
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
In this paper, we propose a novel feature space adaptation technique to improve the robustness of speech recognition in noisy environments. Histogram equalization (HEQ) is an effe...