Speech Enhancement Algorithm based on Reassigned Spectrogram and Auditory Masking

Jie Wang, Chengcheng Yang, Manlu Huang, Linhuang Yan, Jinqiu Sang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

A single channel speech enhancement algorithm is proposed based on reassigned spectrogram and masking properties of the human auditory system. According to the strong correlation of speech harmonics, the correlation of adjacent frames and that of harmonics of the reassigned spectrogram are adopted to control the forgetting factor of the two-step-decision-directed method, and it can suppress the non-speech components better. Then, the estimated speech spectra is used to compute the noise masking threshold of a perceptual gain factor according to the masking properties of the human ear. Experimental results show that the proposed algorithm can improve the intelligibility of speech signals while removing the background noise.

Original languageEnglish
Title of host publication2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages771-778
Number of pages8
ISBN (Electronic)9789881476852
DOIs
StatePublished - 2 Jul 2018
Externally publishedYes
Event10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Honolulu, United States
Duration: 12 Nov 201815 Nov 2018

Publication series

Name2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

Conference

Conference10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018
Country/TerritoryUnited States
CityHonolulu
Period12/11/1815/11/18

Fingerprint

Dive into the research topics of 'Speech Enhancement Algorithm based on Reassigned Spectrogram and Auditory Masking'. Together they form a unique fingerprint.

Cite this