75 search results - page 3 / 15 » An auditory-based feature for robust speech recognition |
ICASSP
2010
IEEE
13 years 7 months ago
2010
IEEE
This paper presents a new robust feature extraction algorithm based on a modified approach to power bias subtraction combined with applying a threshold to the power spectral dens...
NAACL
1994
13 years 9 months ago
1994
A new mapping algorithm for speech recognition relates the features of simultaneous recordings of clean and noisy speech. The model is a piecewise nonfinear transformation appfied...
ICASSP
2010
IEEE
13 years 6 months ago
2010
IEEE
The REMOS (REverberation MOdeling for Speech recognition) concept for reverberation-robust distant-talking speech recognition, introduced in [1] for melspectral features, is exten...
INTERSPEECH
2010
13 years 3 months ago
2010
Over the years, the focus in noise robust speech recognition has shifted from noise robust features to model based techniques such as parallel model combination and uncertainty de...
ICASSP
2011
IEEE
13 years 7 days ago
2011
IEEE
Almost all current automatic speech recognition (ASR) systems conventionally append delta and double-delta cepstral features to static cepstral features. In this work we describe ...