LAUSR.org creates dashboard-style pages of related content for over 1.5 million academic articles. Sign Up to like articles & get recommendations!

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

Photo from wikipedia

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… Click to show full abstract

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 acoustic-phonetic 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.

Keywords: phonetic attention; phonetic approach; acoustic phonetic; neural acoustic; speaker verification

Journal Title: IEEE Signal Processing Letters
Year Published: 2022

Link to full text (if available)


Share on Social Media:                               Sign Up to like & get
recommendations!

Related content

More Information              News              Social Media              Video              Recommended



                Click one of the above tabs to view related content.