Novel Phase Encoded Mel Cepstral Features for Speaker Verification
In this paper, we propose novel phase encoded Mel cepstral coefficients (PEMCC) features for Automatic Speaker Verification (ASV) task. This is motivated by recently proposed phase encoding scheme that uses causal delta dominance condition (CDD). In particular, we got on an average of 80% reduction in log-spectral distortion (LSD) for reconstruction error compared to its magnitude spectrum counterpart, using CDD scheme. This result indicates that phase encoded magnitude spectrum is having better reconstruction capability. The experiments of proposed PEMCC features are carried out on standard statistically meaningful NIST 2002 SRE database and the performance is compared with baseline MFCC features. Furthermore, score-level fusion of MFCC+PEMCC features gave better results for GMM-UBM-based system, i-vector probabilistic linear discriminant analysis (PLDA)-based system and i-vector Cosine Distance Scoring (CDS)-based system over MFCC and PEMCC features alone. This illustrates, the proposed PEMCC features capture complementary speaker-specific information.
KeywordsSpeaker verification Causal delta dominance Phase encoding i-Vector Cosine distance scoring Probiblistic linear discriminant analysis
- 5.Kenny, P.: Bayesian speaker verification with heavy-tailed priors. In: Speaker Odyssey. p. 14 (2010)Google Scholar
- 6.Martin, A., Przybocki, M.: The NIST year 2002 speaker recognition evaluation plan (2001)Google Scholar
- 8.Quatieri, T.F.: Discrete-Time Speech Signal Processing: Principles and Practice. Pearson Education, India (2006)Google Scholar
- 10.Tak, R., Kamble, M.R., Patil, H.A.: Analysis-by-synthesis approach for phase encoded Mel cepstral features to detect spoofed speech. In: Submited for possible publication in INTERSPEECH (2017)Google Scholar
- 11.Seelamantula, C.S.: Phase-encoded speech spectrograms. In: INTERSPEECH, San Francisco, USA, pp. 1775–1779 (2016)Google Scholar