Exemplar-based Recognition of Speech in Highly Variable Noise
Antti Hurmalainen, Katariina Mahkonen, Jort Florent Gemmeke, Tuomas I. Virtanen · Lirias · 2011
Robustness against varying background noise is a crucial re-quirement for the use of automatic speech recognition in ev-eryday situations. In previous work, we proposed an exemplar-based recognition system for tackling the issue at low SNRs. In this work, we compare several exemplar-based factorisation and decoding algorithms in pursuit of higher noise robustness. The algorithms are evaluated using the PASCAL CHiME chal-lenge corpus, which contains multiple speakers and authentic living room noise at six SNRs ranging from 9 to-6 dB. The results show that the proposed exemplar-based techniques of-fer a substantial improvement in the noise robustness of speech recognition. Index Terms: automatic speech recognition, exemplar-based, noise robustness, sparse representation