Opening the Black Box of wav2vec Feature Encoder

27 October 2022

Papers citing "Opening the Black Box of wav2vec Feature Encoder"

4 / 4 papers shown

Title
Discrete Speech Unit Extraction via Independent Component Analysis Tomohiko Nakamura Kwanghee Choi Keigo Hojo Yoshiaki Bando Satoru Fukayama Shinji Watanabe 43 0 0 11 Jan 2025
Self-Supervised Speech Representations are More Phonetic than Semantic Kwanghee Choi Ankita Pasad Tomohiko Nakamura Satoru Fukayama Karen Livescu Shinji Watanabe 39 14 0 12 Jun 2024
Comparative layer-wise analysis of self-supervised speech models Ankita Pasad Bowen Shi Karen Livescu SSL 33 109 0 08 Nov 2022
Exploring wav2vec 2.0 on speaker verification and language identification Zhiyun Fan Meng Li Shiyu Zhou Bo Xu 117 202 0 11 Dec 2020