Conference paper
Simplified lstms for speech recognition
George Saon, Zoltan Tuske, et al.
ASRU 2019
This paper exploits the fact that when GMM and SVM classifiers with roughly the same level of performance exhibit uncorrelated errors they can be combined to produce a better classifier. The gain accrues from combining the descriptive strength of GMM models with the discriminative power of SVM classifiers. This idea, first exploited in the context of speaker recognition [1, 2], is applied to speech recognition - specifically to a digit recognition task in a noisy environment - with significant gains in performance.
George Saon, Zoltan Tuske, et al.
ASRU 2019
George Saon
ICASSP 2006
Ramesh A. Gopinath
IEEE TSP
Wei Zhang, Xiaodong Cui, et al.
INTERSPEECH 2019