Speaker-Phonetic Vector Estimation for Short Duration Speaker Verification

Traditional acoustic-phonetic approach makes use of both spectral and phonetic information when comparing the voice of speakers. While phonetic units are not equally informative, the phonetic context of speech plays an important role in speaker verification (SV). In this paper, we propose a neural acousticphonetic approach that learns to dynamically assign differentiated weights to spectral features for SV. Such differentiated weights form a phonetic attention mask (PAM). The neural acoustic-phonetic framework consists of two training pipelines, one for SV and another for speech recognition. Through the PAM, we leverage the phonetic information for SV. We evaluate the proposed neural acoustic-phonetic framework on the RSR2015 database Part III corpus, that consists of random digit strings. We show that the proposed framework with PAM consistently outperforms baseline with an equal error rate reduction of 13.45% and 10.20% for female and male data, respectively.

show abstract

Speaker-Phonetic Vector Estimation for Short Duration Speaker Verification

Cited by 3 publications

References 15 publications

Phoneme Specific Modelling and Scoring Techniques for Anti Spoofing System

Phoneme Specific Modelling and Scoring Techniques for Anti Spoofing System

Generalized Variability Model for Speaker Verification

Neural Acoustic-Phonetic Approach for Speaker Verification With Phonetic Attention Mask

Contact Info

Product

Resources

About