Rethinking Session Variability: Leveraging Session Embeddings for Session Robustness in Speaker Verification

In the field of speaker verification, session or channel variability poses a significant challenge. While many contemporary methods aim to disentangle session information from speaker embeddings, we introduce a novel approach using an additional embedding to represent the session information. This i...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 12321 - 12325
Main Authors Heo, Hee-Soo, Nam, KiHyun, Lee, Bong-Jin, Kwon, Youngki, Lee, Minjae, Kim, You Jin, Chung, Joon Son
Format Conference Proceeding
LanguageEnglish
Published IEEE 14.04.2024
Subjects
Calibration
Data mining
Degradation
Robustness
session information
Signal processing
speaker embedding
Speaker verification
Speech processing
Training
Online AccessGet full text

Cover

More Information
Summary:In the field of speaker verification, session or channel variability poses a significant challenge. While many contemporary methods aim to disentangle session information from speaker embeddings, we introduce a novel approach using an additional embedding to represent the session information. This is achieved by training an auxiliary network appended to the speaker embedding extractor which remains fixed in this training process. This results in two similarity scores: one for the speakers information and one for the session information. The latter score acts as a compensator for the former that might be skewed due to session variations. Our extensive experiments demonstrate that session information can be effectively compensated without retraining of the embedding extractor.
ISSN:2379-190X
DOI:10.1109/ICASSP48485.2024.10445987