Robustness of ad hoc microphone clustering using speaker embeddings: evaluation under realistic and challenging scenarios

Abstract Speaker embeddings, from the ECAPA-TDNN speaker verification network, were recently introduced as features for the task of clustering microphones in ad hoc arrays. Our previous work demonstrated that, in comparison to signal-based Mod-MFCC features, using speaker embeddings yielded a more r...

Full description

Bibliographic Details
Published in:EURASIP Journal on Audio, Speech, and Music Processing
Main Authors: Stijn Kindt, Jenthe Thienpondt, Luca Becker, Nilesh Madhu
Format: Article
Language:English
Published: SpringerOpen 2023-10-01
Subjects:
Online Access:https://doi.org/10.1186/s13636-023-00310-w