Spectro-temporal smoothed auditory spectra for robust speaker identification

Ting H. Lin*, Chung Chien Hsu, Tai-Shih Chi

*Corresponding author for this work

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

Abstract

The performance of conventional speaker identification systems is severely compromised by interference, such as additive or convolutional noises. High-level information of the speaker provides more robust cues for identifying speakers. This paper proposes an auditory-model based spectro-temporal modulation filtering (STMF) process to capture high-level information for robust speaker identification. Text-independent closed-set speaker identification simulations are conducted on TIMIT and GRID corpora to evaluate the robustness of Auditory Cepstral Coefficients (ACCs) after the STMF process. Simulation results show ACCs' substantial improvement over conventional MFCCs in all SNR conditions. The superior noise-suppression performance of STMF to newly developed Auditory-based Nonnegative Tensor Cepstral Coefficients (ANTCCs) is also demonstrated in low SNR conditions.

Original languageEnglish
Title of host publication2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010 - Proceedings
Pages313-317
Number of pages5
DOIs
StatePublished - 1 Dec 2010
Event2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010 - Tainan, Taiwan
Duration: 29 Nov 20103 Dec 2010

Publication series

Name2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010 - Proceedings

Conference

Conference2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010
CountryTaiwan
CityTainan
Period29/11/103/12/10

Keywords

  • Auditory feature
  • Gaussian mixture model
  • Speaker identification
  • Spectro-temporal modulation

Fingerprint Dive into the research topics of 'Spectro-temporal smoothed auditory spectra for robust speaker identification'. Together they form a unique fingerprint.

Cite this