On the Estimation and the Use of Confusion-Matrices for Improving ASR Accuracy

Caballero Morales, Omar and Cox, Stephen (2009) On the Estimation and the Use of Confusion-Matrices for Improving ASR Accuracy. In: 10th Annual Conference of the International Speech Communication Association (INTERSPEECH), 2009-09-06 - 2009-09-10.

Full text not available from this repository. (Request a copy)

Abstract

In previous work, we described how learning the pattern of recognition errors made by an individual using a certain ASR system leads to increased recognition accuracy compared with a standard MLLR adaptation approach. This was the case for low-intelligibility speakers with dysarthric speech, but no improvement was observed for normal speakers. In this paper, we describe an alternative method for obtaining the training data for confusion-matrix estimation for normal speakers which is more effective than our previous technique. We also address the issue of data sparsity in estimation of confusion-matrices by using non-negative matrix factorization (NMF) to discover structure within them. The confusion-matrix estimates made using these techniques are integrated into the ASR process using a technique termed as "metamodels", and the results presented here show statistically significant gains in word recognition accuracy when applied to normal speech.

Item Type: Conference or Workshop Item (Paper)
Faculty \ School: Faculty of Science > School of Computing Sciences
Related URLs:
Depositing User: Nicola Talbot
Date Deposited: 14 Mar 2011 09:39
Last Modified: 22 Apr 2020 08:58
URI: https://ueaeprints.uea.ac.uk/id/eprint/26038
DOI:

Actions (login required)

View Item View Item