Towards Automatic Assessment of Self-Supervised Speech Models using Rank

v1v2 (latest)

Towards Automatic Assessment of Self-Supervised Speech Models using Rank

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024

16 September 2024

Zakaria Aldeneh

Tatiana Likhomanenko

ArXiv (abs)PDF HTML

Papers citing "Towards Automatic Assessment of Self-Supervised Speech Models using Rank"

14 / 14 papers shown

Title
Unify Variables in Neural Scaling Laws for General Audio Representations via Embedding Effective Rank Xuyao Deng Yanjie Sun Yong Dou Kele Xu 89 0 0 13 Oct 2025
A Large-Scale Evaluation of Speech Foundation Models Shu-Wen Yang Heng-Jui Chang Zili Huang Andy T. Liu Cheng-I Jeff Lai ... Kushal Lakhotia Shang-Wen Li Abdelrahman Mohamed Shinji Watanabe Hung-yi Lee 224 54 0 15 Apr 2024
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures Vimal Thilak Chen Huang Omid Saremi Laurent Dinh Hanlin Goh Preetum Nakkiran Josh Susskind Etai Littwin 262 20 0 07 Dec 2023
Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic ComputeInterspeech (Interspeech), 2023 William Chen Xuankai Chang Yifan Peng Zhaoheng Ni Soumi Maiti Shinji Watanabe SSL 233 29 0 11 Jun 2023
How to Estimate Model Transferability of Pre-Trained Speech Models?Interspeech (Interspeech), 2023 Zih-Ching Chen Chao-Han Huck Yang Yue Liu Yu Zhang Nanxin Chen Shoufeng Chang Rohit Prabhavalkar Hung-yi Lee Tara N. Sainath 392 11 0 01 Jun 2023
Unsupervised Embedding Quality Evaluation Anton Tsitsulin Marina Munkhoeva Bryan Perozzi SSL 192 10 0 26 May 2023
On the Stepwise Nature of Self-Supervised LearningInternational Conference on Machine Learning (ICML), 2023 James B. Simon Maksis Knutins Liu Ziyin Daniel Geisz Abraham J. Fetterman Joshua Albrecht SSL 269 38 0 27 Mar 2023
RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rankInternational Conference on Machine Learning (ICML), 2022 Q. Garrido Randall Balestriero Laurent Najman Yann LeCun SSL 246 110 0 05 Oct 2022
Self-Supervised Speech Representation Learning: A ReviewIEEE Journal on Selected Topics in Signal Processing (IEEE JSTSP), 2022 Abdel-rahman Mohamed Hung-yi Lee Lasse Borgholt Jakob Drachmann Havtorn Joakim Edin ... Shang-Wen Li Karen Livescu Lars Maaløe Tara N. Sainath Shinji Watanabe SSL AI4TS 578 435 0 21 May 2022
Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative FeaturesAAAI Conference on Artificial Intelligence (AAAI), 2022 Neha Kalibhat Kanika Narang Hamed Firooz Maziar Sanjabi Soheil Feizi SSL 377 11 0 03 Mar 2022
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing Sanyuan Chen Chengyi Wang Zhengyang Chen Yu-Huan Wu Shujie Liu ... Yao Qian Jian Wu Micheal Zeng Xiangzhan Yu Furu Wei SSL 735 2,573 0 26 Oct 2021
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden UnitsIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2021 Wei-Ning Hsu Benjamin Bolte Yifan Hao Kushal Lakhotia Ruslan Salakhutdinov Abdel-rahman Mohamed SSL 492 3,904 0 14 Jun 2021
On Feature Decorrelation in Self-Supervised LearningIEEE International Conference on Computer Vision (ICCV), 2021 Tianyu Hua Wenxiao Wang Zihui Xue Sucheng Ren Yue Wang Hang Zhao SSL OOD 421 210 0 02 May 2021
VoxCeleb: a large-scale speaker identification dataset Arsha Nagrani Joon Son Chung Andrew Zisserman 981 2,529 0 26 Jun 2017