Feature Selection Based on CQCCs for Automatic Speaker Verification Spoofing

Robust Automatic Speaker Verification has become increasingly desirable in recent years with the growing trend toward remote security verification procedures for telephone banking, bio-metric security measures and similar applications. While many approaches have been applied to this problem, Genetic Programming offers inherent feature selection and solutions that can be meaningfully analyzed, making it well suited for this task. This chapter introduces a Genetic Programming system to evolve programs capable of speaker verification and evaluates its performance with the publicly available TIMIT corpora. Also presented are the effects of a simulated telephone network on classification results which highlight the principal advantage, namely robustness to both additive and convolutive noise.

Download Full-text

Feature-switching: Dynamic feature selection for an i-vector based speaker verification system

Speech Communication ◽

10.1016/j.specom.2017.08.004 ◽

2017 ◽

Vol 93 ◽

pp. 53-62 ◽

Cited By ~ 3

Author(s):

Saranya M.S. ◽

Padmanabhan R. ◽

Hema A. Murthy

Keyword(s):

Feature Selection ◽

Speaker Verification ◽

Dynamic Feature ◽

Verification System ◽

Switching Dynamic ◽

Selection For

Download Full-text

Particle Swarm Optimization for Feature Selection in Speaker Verification

Applications of Evolutionary Computation - Lecture Notes in Computer Science ◽

10.1007/978-3-642-12239-2_39 ◽

2010 ◽

pp. 371-380 ◽

Cited By ~ 1

Author(s):

Shahla Nemati ◽

Mohammad Ehsan Basiri

Keyword(s):

Feature Selection ◽

Particle Swarm Optimization ◽

Speaker Verification ◽

Particle Swarm ◽

Swarm Optimization

Download Full-text

Genetic Programming for Robust Text Independent Speaker Verification

International Journal of Signs and Semiotic Systems ◽

10.4018/ijsss.2012070101 ◽

2012 ◽

Vol 2 (2) ◽

pp. 1-22

Author(s):

Peter Day ◽

Asoke K. Nandi

Keyword(s):

Feature Selection ◽

Genetic Programming ◽

Speaker Verification ◽

Telephone Network ◽

Programming System ◽

Security Measures ◽

Inherent Feature ◽

Text Independent Speaker Verification ◽

Remote Security ◽

Principal Advantage

Robust Automatic Speaker Verification has become increasingly desirable in recent years with the growing trend toward remote security verification procedures for telephone banking, bio-metric security measures and similar applications. While many approaches have been applied to this problem, Genetic Programming offers inherent feature selection and solutions that can be meaningfully analyzed, making it well suited for this task. This article introduces a Genetic Programming system to evolve programs capable of speaker verification and evaluates its performance with the publicly available TIMIT corpora. Also presented are the effects of a simulated telephone network on classification results which highlight the principal advantage, namely robustness to both additive and convolutive noise.

Download Full-text