Joint evaluation of multiple speech patterns for speech recognition and training

Nair, Nishanth Ulhas and Sreenivas, TV (2010) Joint evaluation of multiple speech patterns for speech recognition and training. In: Computer Speech & Language, 24 (2). pp. 307-340.

PDF 14.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

We are addressing the novel problem of jointly evaluating multiple speech patterns for automatic speech recognition and training. We propose solutions based on both the non-parametric dynamic time warping (DTW) algorithm, and the parametric hidden Markov model (HMM). We show that a hybrid approach is quite effective for the application of noisy speech recognition. We extend the concept to HMM training wherein some patterns may be noisy or distorted. Utilizing the concept of ``virtual pattern'' developed for joint evaluation, we propose selective iterative training of HMMs. Evaluating these algorithms for burst/transient noisy speech and isolated word recognition, significant improvement in recognition accuracy is obtained using the new algorithms over those which do not utilize the joint evaluation strategy.

Item Type:	Journal Article
Publication:	Computer Speech & Language
Publisher:	Elsevier Science
Additional Information:	Copyright for this article belongs to Elsevier Science.
Keywords:	Joint recognition; Joint decoding; Dynamic time warping; Viterbi algorithm; Hidden Markov models; Multi pattern analysis; Robust speech recognition; Selective HMM training; Multi pattern dynamic time warping
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	01 Dec 2009 05:50
Last Modified:	19 Sep 2010 05:53
URI:	http://eprints.iisc.ac.in/id/eprint/25030

Actions (login required)

View Item