Novel algorithm for speech segregation by optimized k-means of statistical properties of clustered features

Hasan Almgotir Kadhim*, Lok Woo, Satnam Dlay

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

To simplify the jobs of speaker diarization and speech separation, at first, speech signal should be segregated to two speech formats, dialog and mixture. This paper describes a new algorithm which achieves that first step efficiently. The algorithm is based on Perceptual Linear Predictive feature extraction, optimized k-means and both top-down & bottom-up scenarios. After extracting features of the observation signal, k-means clusters the statistical properties such as variances of the PDF (histogram) of clustered extracted features. k-means is optimized by discounting the worst pattern of clustering step through doing the k-means procedure twice. The feedback loop is necessary for the guiding of the optimized k-means by exploiting the attributes of ordinary k-means. The results of segregation are excellent. The calculated diarization error rate of outputs is very limited.

Original languageEnglish
Title of host publicationProceedings of 2015 IEEE International Conference on Progress in Informatics and Computing, PIC 2015
EditorsLiang Xiao, Yinglin Wang
PublisherIEEE
Pages286-291
Number of pages6
ISBN (Electronic)9781467390880
ISBN (Print)9781467380867
DOIs
Publication statusPublished - 13 Jun 2016
Externally publishedYes
Event3rd IEEE International Conference on Progress in Informatics and Computing, PIC 2015 - Nanjing, China
Duration: 18 Dec 201520 Dec 2015

Conference

Conference3rd IEEE International Conference on Progress in Informatics and Computing, PIC 2015
CountryChina
CityNanjing
Period18/12/1520/12/15

Fingerprint Dive into the research topics of 'Novel algorithm for speech segregation by optimized k-means of statistical properties of clustered features'. Together they form a unique fingerprint.

Cite this