Contrasting the Effects of Different Frequency Bands on Speaker and Accent Identification

Author

Safavi, Saeid ; Hanani, Abualsoud ; Russell, Matthew ; Jancovic, P. ; Carey, M.J.

Author_Institution

Sch. of Electron., Electr., & Comput. Eng., Univ. of Birmingham, Birmingham, UK

Volume

19

Issue

12

fYear

2012

Firstpage

829

Lastpage

832

Abstract

This letter presents an experimental study investigating the effect of frequency sub-bands on regional accent identification (AID) and speaker identification (SID) performance on the ABI-1 corpus. The AID and SID systems are based on Gaussian mixture modeling. The SID experiments show up to 100% accuracy when using the full 11.025 kHz bandwidth. The best AID performance of 60.34% is obtained when using band-pass filtered (0.23-3.4 kHz) speech. The experiments using isolated narrow sub-bands show that the regions (0-0.77 kHz) and (3.40-11.02 kHz) are the most useful for SID, while those in the region (0.34-3.44 kHz) are best for AID. AID experiments are also performed with intersession variability compensation, which provides the biggest performance gain in the (2.23-5.25 kHz) region.

Keywords

Gaussian processes; band-pass filters; natural language processing; speaker recognition; ABI-1 corpus; AID systems; Gaussian mixture modeling; SID systems; accent identification; band-pass filter; bandwidth 11.025 kHz; frequency 0.23 kHz to 11.02 kHz; frequency bands effects; frequency sub-bands effect; speaker identification; Accuracy; Adaptation models; Band pass filters; Bandwidth; Hidden Markov models; Speech; Training; ABI-1; Gaussian mixture model; accent identification; bandwidth; frequency region; intersession variability compensation; speaker identification; sub-band;

fLanguage

English

Journal_Title

Signal Processing Letters, IEEE

Publisher

ieee

ISSN

1070-9908

Type

jour

DOI

10.1109/LSP.2012.2221697

Filename

6317140