cs.CLOct 31, 2026

GSLM2: Multi-Stream Speech Representation Learning and Generative Spoken Language Modeling

Authors: Yosuke Higuchi, Tom Fizycki, Mahi Luthra, Charles-Éric Saint-James, Azeez Syed, Angel Villar-Corrales, Mido Assran, Nicolas Ballas, 

Organizations: Meta Superintelligence Labs · Université Paris Dauphine-PSL · AMI Labs · Doctolib · 

Abstract

Generative spoken language models (SLMs) offer a route to learning linguistic structure purely from speech, yet they lag far behind text-based models in both capability and data scaling efficiency. We identify two bottlenecks underlying this gap: the limited linguistic quality of existing speech units and the reliance on a single stream of discrete units to represent speech. Multiple codebooks are widely used to encode acoustic features but rarely to represent speech semantics. We present GSLM2, which learns and models complementary properties of speech at multiple levels of abstraction. Its encoder, SpidR 2.0, uses self-supervised learning with differentiable prediction heads to induce high-quality discrete units at multiple levels. A multi-stream SLM then jointly models these units using a shared temporal backbone, stream-specific predictors, and an autoregressive head that captures cross-stream dependencies. Across training data sizes and model scales, up to 6M hours and 6.5B parameters, GSLM2 consistently improves linguistic competence while scaling more efficiently with data. As a result, it substantially narrows the gap between spoken and text-based LMs; across read and conversational speech domains, we shrink the gap by about two orders of magnitude on sWuggy, sBLIMP, and tSC, while also outperforming competitive speech-text systems on all three tasks. We open-source the training code and model checkpoints at https://github.com/facebookresearch/gslm2.

Figures & tables

Appendix figures & tables38 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation

    Mar 5, 2026Luca Della Libera, Cem Subakan, Mirco RavanelliSpeech Language ModelsAutoregressive Language Modeling

  2. On the Effect of Segmentation Width and Cluster Size on Speech Resynthesis and Continuation in Generative Spoken Language Models

    Jun 22, 2026Shunsuke Kando, Wataru Nakata, Shinnosuke Takamichi +1Speech ProcessingSpeech Language Models