alexa Noise Adaptive Training for Robust Automatic Speech Recognition
Biomedical Sciences

Biomedical Sciences

Journal of Bioengineering & Biomedical Science

Author(s): Ozlem Kalinli, Michael L Seltzer

Abstract Share this page

In traditional methods for noise robust automatic speech recognition, the acoustic models are typically trained using clean speech or using multi-condition data that is processed by the same feature enhancement algorithm expected to be used in decoding. In this paper, we propose a noise adaptive training (NAT) algorithm that can be applied to all training data that normalizes the environmental distortion as part of the model training. In contrast to feature enhancement methods, NAT estimates the underlying “pseudo-clean” model parameters directly without relying on point estimates of the clean speech features as an intermediate step. The pseudo-clean model parameters learned with NAT are later used with vector Taylor series (VTS) model adaptation for decoding noisy utterances at test time. Experiments performed on the Aurora 2 and Aurora 3 tasks demonstrate that the proposed NAT method obtain relative improvements of 18.83% and 32.02%, respectively, over VTS model adaptation.

  • To read the full article Visit
  • Open Access
This article was published in IEEE Trans. Audio, Speech, Lang Process and referenced in Journal of Bioengineering & Biomedical Science

Relevant Expert PPTs

Relevant Speaker PPTs

Recommended Conferences

Relevant Topics

Peer Reviewed Journals
Make the best use of Scientific Research and information from our 700 + peer reviewed, Open Access Journals
International Conferences 2017-18
Meet Inspiring Speakers and Experts at our 3000+ Global Annual Meetings

Contact Us

© 2008-2017 OMICS International - Open Access Publisher. Best viewed in Mozilla Firefox | Google Chrome | Above IE 7.0 version