cs.CLNov 10, 2026

Distributionally Robust BEST-RQ For Speech Representation Learning

Authors: Muhammad Khan, Xiaodong Cui, Brian Kingsbury, George Saon

Organizations: Rensselaer Polytechnic Institute · IBM Research

Abstract

BEST-RQ, based on random projection and quantization, has been a well-established self-supervised learning approach to learn speech representations from large-scale unlabeled audio due to its high performance and efficiency. However, in BEST-RQ representations learned by random quantization can be sensitive to the choice of quantization targets. To address this issue, we propose a distributionally robust extension of BEST-RQ that seeks representations robust across multiple quantization configurations. Specifically, we define groups by codebooks and formulate the training as a group Distributionally Robust Optimization (DRO) problem. Rather than optimizing solely for the average loss across groups, our approach adaptively reweights groups to emphasize those performing poorly. Additionally, we regularize DRO with a Kullback-Leibler divergence to prevent excessive distribution deviation. We evaluate our approach on the Multilingual LibriSpeech dataset and show that the distributionally robust BEST-RQ achieves superior performance over the conventional uniform average across multiple codebooks.

Figures & tables

Explore similar work

CardsList
  1. Enhancing BEST-RQ Pseudo-Label Quality through Online Refinement for Automatic Speech Recognition

    Jun 24, 2026Jingjing Xu, Zijian Yang, Mohammad Zeineldeen +3Automatic Speech RecognitionVector Quantization

  2. BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations

    Jun 29, 2026Ludovic K. Tuncay, Etienne Labbé, Thomas PellegriniAudio Representation LearningSelf-Supervised Pre-Training

  3. SepRQ : Self-Supervised Speech Mixture Representation Learning via Mask-Free, Multi-Scale Source Separation

    Oct 3, 2026Séverin Baroudi, Hervé Bredin, Ricard MarxerSelf-Supervised Speech Representation LearningSpeech Separation