Speaker identification using HHT spectrum features

Jia Wei Liu, Jia Ching Wang, Chang Hong Lin

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

2 Scopus citations

Abstract

This paper proposes new acoustical features based on Hilbert Huang transform (HHT) for speaker identification. HHT is a powerful analysis method to obtain instantaneous frequency (IF). First, empirical ensemble empirical mode decomposition (EEMD) is used to generate intrinsic mode functions (IMFs). The Hilbert transform is then applied to IMFs to compute the instantaneous frequencies. With the obtained instantaneous frequencies, two new acoustical features are presented. The first acoustical feature is the weighted mean IF in each IMF while the second is the IF difference between two consecutive IMFs. This study adopts Gaussian mixture model (GMM) to train and test the speaker models. Finally, the experiments conducted on CHAIN corpus demonstrate the superiority of the proposed acoustical features.

Original languageEnglish
Title of host publicationProceedings - 2011 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2011
Pages145-148
Number of pages4
DOIs
StatePublished - 2011
Event16th Annual Conference on Technologies and Applications of Artificial Intelligence, TAAI 2011 - Chung-Li, Taiwan
Duration: 11 Nov 201113 Nov 2011

Publication series

NameProceedings - 2011 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2011

Conference

Conference16th Annual Conference on Technologies and Applications of Artificial Intelligence, TAAI 2011
Country/TerritoryTaiwan
CityChung-Li
Period11/11/1113/11/11

Keywords

  • Empirical mode decomposition (EMD)
  • Hilbert Huang transform
  • Instantaneous frequency
  • Speaker identification
  • Speaker recognition

Fingerprint

Dive into the research topics of 'Speaker identification using HHT spectrum features'. Together they form a unique fingerprint.

Cite this