Tandem connectionist feature stream extraction for conventional HMM systems

Hermansky, Hynek; Ellis, Daniel P. W.; Sharma, Sangita

Hidden Markov model speech recognition systems typically use Gaussian mixture models to estimate the distributions of decorrelated acoustic feature vectors that correspond to individual subword units. By contrast, hybrid connectionist-HMM systems use discriminatively-trained neural networks to estimate the probability distribution among subword units given the acoustic observations. In this work we show a large improvement in word recognition performance by combining neural-net discriminative feature processing with Gaussian-mixture distribution modeling. By training the network to generate the subword probability posteriors, then using transformations of these estimates as the base features for a conventionally-trained Gaussian-mixture based system, we achieve relative error rate reductions of 35% or more on the multicondition Aurora noisy continuous digits task


Also Published In

2000 IEEE International Conference on Acoustics, Speech, and Signal Processing: Proceedings, 5-9 June, 2000, Hilton Hotel and Convention Center, Istanbul, Turkey

More About This Work

Academic Units
Electrical Engineering
Published Here
July 3, 2012