Spectro-temporal modulation energy based mask for robust speaker identification

The Journal of the Acoustical Society of America
Tai-Shih ChiChung-Chien Hsu

Abstract

Spectro-temporal modulations of speech encode speech structures and speaker characteristics. An algorithm which distinguishes speech from non-speech based on spectro-temporal modulation energies is proposed and evaluated in robust text-independent closed-set speaker identification simulations using the TIMIT and GRID corpora. Simulation results show the proposed method produces much higher speaker identification rates in all signal-to-noise ratio (SNR) conditions than the baseline system using mel-frequency cepstral coefficients. In addition, the proposed method also outperforms the system, which uses auditory-based nonnegative tensor cepstral coefficients [Q. Wu and L. Zhang, "Auditory sparse representation for robust speaker recognition based on tensor structure," EURASIP J. Audio, Speech, Music Process. 2008, 578612 (2008)], in low SNR (≤ 10 dB) conditions.

References

Sep 15, 2005·The Journal of the Acoustical Society of America·Taishih ChiShihab A Shamma
Dec 2, 2006·The Journal of the Acoustical Society of America·Martin CookeXu Shao
Jan 18, 2007·The Journal of the Acoustical Society of America·Douglas S BrungartDeLiang Wang
Apr 10, 2009·The Journal of the Acoustical Society of America·DeLiang WangThomas Lunner
Sep 11, 2009·The Journal of the Acoustical Society of America·Gibak KimPhilipos C Loizou

❮ Previous
Next ❯

Citations

Jul 9, 2016·PloS One·Md Atiqul IslamMuhammad Shamsul Arefeen Zilany

❮ Previous
Next ❯

Related Concepts

Related Feeds

Auditory Perception

Auditory perception is the ability to receive and interpret information attained by the ears. Here is the latest research on factors and underlying mechanisms that influence auditory perception.

Related Papers

The Journal of the Acoustical Society of America
Inge BronsWouter A Dreschler
The Journal of the Acoustical Society of America
Kun Han, Deliang Wang
The Journal of the Acoustical Society of America
Mahnaz AhmadiDonal G Sinex
© 2021 Meta ULC. All rights reserved