Speech emotional features measured by power-law distribution based on electroglottography

Lijiang Chen, Xia Mao, Yuli Xue, Mitsuru Ishizuka

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

1 Citation (Scopus)

Abstract

This study was designed to introduce a kind of novel speech emotional features extracted from Electroglot-tography (EGG). These features were obtained from the power-law distribution coefficient (PLDC) of fundamental frequency (F 0) and duration parameters. First, the segments of silence, voiced and unvoiced (SUV) were distinguished by combining the EGG and speech information. Second, the F 0 of voiced segment and the first-order differential of F 0 was obtained by a cepstrum method. Third, PLDC of voiced segment as well as the pitch rise and pitch down duration were calculated. Simulation results show that the proposed features are closely connected with emotions. Experiments based on Support Vector Machine (SV M) are carried out. The results show that proposed features are better than those commonly used in the case of speaker independent emotion recognition.

Original languageEnglish
Title of host publicationBIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing
Pages131-136
Number of pages6
Publication statusPublished - 2012
Externally publishedYes
EventInternational Conference on Bio-inspired Systems and Signal Processing, BIOSIGNALS 2012 - Vilamoura, Algarve
Duration: 2012 Feb 12012 Feb 4

Other

OtherInternational Conference on Bio-inspired Systems and Signal Processing, BIOSIGNALS 2012
CityVilamoura, Algarve
Period12/2/112/2/4

Keywords

  • Electroglottography
  • Power-law distribution
  • Speech emotional features

ASJC Scopus subject areas

  • Signal Processing

Fingerprint Dive into the research topics of 'Speech emotional features measured by power-law distribution based on electroglottography'. Together they form a unique fingerprint.

Cite this