Robustness of speaker recognition from noisy speech samples and mismatched languages

Al-Noori, AHY, Li, FF ORCID: https://orcid.org/0000-0001-9053-963X and Duncan, PJ 2016, Robustness of speaker recognition from noisy speech samples and mismatched languages , in: 140th Convention-AES, 4-7 June 2016, Paris.

	Microsoft Word - Published Version Restricted to Repository staff only Download (4MB) | Request a copy
	PDF - Published Version Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Speaker recognition systems can typically attain high performance in ideal conditions. However, significant degradations in accuracy are found in channel-mismatched scenarios. Non-stationary environmental noises and their variations are listed at the top of speaker recognition challenges. Gammtone frequency cepstral coefficient method (GFCC) has been developed to improve the robustness of speaker recognition. This paper presents systematic comparisons between performance of GFCC and conventional MFCC based speaker verification systems with a purposely collected noisy speech data set. Furthermore, the current work extends the experiments to include investigations into language independency features in recognition phases. The results show that GFCC has better verification performance in noisy environments than MFCC. However, GFCC show more sensitivity to language mismatch between enrolment and recognition phase.

Item Type:	Conference or Workshop Item (Paper)
Schools:	Schools > School of Computing, Science and Engineering
Journal or Publication Title:	140th Convention-AES
Publisher:	AES
Related URLs:	Organisation
Funders:	The Ministry of Higher education and Scientific research - Iraq
Depositing User:	Mr AHY Al-Noori
Date Deposited:	11 Apr 2016 12:29
Last Modified:	15 Feb 2022 20:37
URI:	https://usir.salford.ac.uk/id/eprint/38710

Actions (login required)

Edit record (repository staff only)