University of Sussex
Browse

File(s) under permanent embargo

Integration of phoneme pattern recognition with hidden Markov models to enhance performance of low level speech recognition

journal contribution
posted on 2023-06-09, 01:16 authored by Mohammed Al-Darkazali, Rupert YoungRupert Young, Chris ChatwinChris Chatwin, Phil BirchPhil Birch
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.

Funding

Speech Recognition; 160516iisp; Iraqi Ministry of Education

History

Publication status

  • Published

File Version

  • Accepted version

Journal

Asian Journal of Physics

ISSN

0971-3093

Publisher

Anita Publications

Issue

6

Volume

25

Department affiliated with

  • Informatics Publications

Full text available

  • No

Peer reviewed?

  • Yes

Legacy Posted Date

2016-05-16

First Compliant Deposit (FCD) Date

2016-05-16

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC