Noise estimation for speech enhancement using minimum-spectral-average and vowel-presence detection approach

Ching Ta Lu, Yung Yue Chen, Jun Hong Shen, Ling Ling Wang, Chung Lin Lei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The accuracy of noise estimation is important for the performance of a speech enhancement system. This study proposes using variable segment length for noise tracking and variable thresholds for the determination of speech-presence probability. Initially, the fundamental frequency is estimated to determine whether a frame is a vowel. In the case of a vowel frame, the segment length increases; meanwhile the threshold for speech-presence is decreased. So the noise magnitude is adequately underestimated. The speech distortion is accordingly reduced in enhanced speech. Conversely, the segment length is rapidly decreased during noise-dominant regions. This enables the noise estimate to be updated quickly and the noise variation to be well tracked, yielding background noise being efficiently removed by the process of speech enhancement. Experimental results show that the proposed method can efficiently track the variation of background noise, enabling the performance of speech enhancement to be improved.

Original languageEnglish
Title of host publicationFrontier Computing - Theory, Technologies and Applications, FC 2016
EditorsNeil Y. Yen, Jason C. Hung
PublisherSpringer Verlag
Pages317-327
Number of pages11
ISBN (Print)9789811031861
DOIs
Publication statusPublished - 2018
Event 5th International Conference on Frontier Computing, FC 2016 - Tokyo, Japan
Duration: 2016 Jul 132016 Jul 15

Publication series

NameLecture Notes in Electrical Engineering
Volume422
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Other

Other 5th International Conference on Frontier Computing, FC 2016
CountryJapan
CityTokyo
Period16-07-1316-07-15

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'Noise estimation for speech enhancement using minimum-spectral-average and vowel-presence detection approach'. Together they form a unique fingerprint.

Cite this