University of Sussex
Browse
On_preprocessing_of_speech_signals.pdf (580.95 kB)

On preprocessing of speech signals

Download (580.95 kB)
journal contribution
posted on 2023-06-07, 15:11 authored by Ayaz Keerio, Bhargav Kumar Mitra, Phil BirchPhil Birch, Rupert YoungRupert Young, Chris ChatwinChris Chatwin
Preprocessing of speech signals is considered a crucial step in the development of a robust and efficient speech or speaker recognition system. In this paper, we present some popular statistical outlier-detection based strategies to segregate the silence/unvoiced part of the speech signal from the voiced portion. The proposed methods are based on the utilization of the 3 s edit rule, and the Hampel Identifier which are compared with the conventional techniques: (i) short-time energy (STE) based methods, and (ii) distribution based methods. The results obtained after applying the proposed strategies on some test voice signals are encouraging

History

Publication status

  • Published

File Version

  • Published version

Journal

International Journal of Signal Processing

ISSN

2070-397X

Publisher

World Academy of Science, Engineering and Technology

Issue

3

Volume

5

Page range

216-222

Department affiliated with

  • Engineering and Design Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2010-04-08

First Open Access (FOA) Date

2018-03-16

First Compliant Deposit (FCD) Date

2018-03-16

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC