Al-darkazali, Mohammed, Young, Rupert, Chatwin, Chris and Birch, Philip (2016) Integration of phoneme pattern recognition with hidden Markov models to enhance performance of low level speech recognition. Asian Journal of Physics, 25 (6). ISSN 0971-3093

PDF - Accepted Version Restricted to SRO admin only Download (2MB)

Abstract

The hidden Markov model (HMM) is commonly employed in automatic speech recognition (ASR). The HMM has been shown to have a good performance in many applications, although it has some well-known limitations in modelling speech. Therefore, the standard HMM topology has been modified in a variety of ways to reduce errors, including factorization of the HMM into multiple-streams. However, the gap between the theoretical representation of speech and its acoustic representation can be further reduced. This paper describes a new method of correcting the HMM based on matching two dimensional templates of word time-frequency patterns to assist in low level speech recognition. This is shown to be a promising method to enhance speech recognition performance.

Item Type:	Article
Keywords:	Pattern matching, image matching, hidden Markov models, automatic speech recognition
Schools and Departments:	School of Engineering and Informatics > Informatics
Subjects:	Q Science > Q Science (General) Q Science > QA Mathematics > QA0101 Elementary mathematics. Arithmetic Q Science > QA Mathematics > QA0075 Electronic computers. Computer science Q Science > QC Physics > QC0221 Acoustics. Sound T Technology > T Technology (General) > T0010 Communication of technical information T Technology > T Technology (General)
Depositing User:	Chris Chatwin
Date Deposited:	16 May 2016 15:58
Last Modified:	29 Mar 2017 16:07
URI:	http://srodev.sussex.ac.uk/id/eprint/61042

View download statistics for this item

📧 Request an update