CONF li:Interspeech:2007/IDIAP Non-linear Spectral Contrast Stretching for In-car Speech Recognition Li, Weifeng Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/papers/2007/li-Interspeech-2007.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/li:rr07-53 Related documents Interspeech-Eurospeech # to appear in html 2007 IDIAP-RR 07-53 In this paper, we present a novel feature normalization method in the log-scaled spectral domain for improving the noise robustness of speech recognition front-ends. In the proposed scheme, a non-linear contrast stretching is added to the outputs of log mel-filterbanks (MFB) to imitate the adaptation of the auditory system under adverse conditions. This is followed by a two-dimensional filter to smooth out the processing artifacts. The proposed MFCC front-ends perform remarkably well on CENSREC-2 in-car database with an average relative improvement of 29.3\% compared to baseline MFCC system. It is also confirmed that the proposed processing in log MFB domain can be integrated with conventional cepstral post-processing techniques to yield further improvements. The proposed algorithm is simple and requires only a small extra computation load. REPORT li:rr07-53/IDIAP Non-linear Spectral Contrast Stretching for In-car Speech Recognition Li, Weifeng Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/reports/2007/li-idiap-rr-07-53.pdf PUBLIC Idiap-RR-53-2007 2007 IDIAP In this paper, we present a novel feature normalization method in the log-scaled spectral domain for improving the noise robustness of speech recognition front-ends. In the proposed scheme, a non-linear contrast stretching is added to the outputs of log mel-filterbanks (MFB) to imitate the adaptation of the auditory system under adverse conditions. This is followed by a two-dimensional filter to smooth out the processing artifacts. The proposed MFCC front-ends perform remarkably well on CENSREC-2 in-car database with an average relative improvement of 29.3\% compared to baseline MFCC system. It is also confirmed that the proposed processing in log MFB domain can be integrated with conventional cepstral post-processing techniques to yield further improvements. The proposed algorithm is simple and requires only a small extra computation load.