pith. sign in

Stab: Speech tokenizer assessment benchmark.arXiv preprint arXiv:2409.02384

Shikhar Vashishth, Harman Singh, Shikhar Bharadwaj, Sriram Ganapathy, Chulayuth Asawaroengchai, Kartik Audhkhasi, Andrew Rosenberg, Ankur Bapna, Bhuvana Ramabhadran · arXiv 2409.02384

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Voxtral TTS

cs.AI · 2026-03-26 · unverdicted · novelty 5.0

Voxtral TTS produces expressive multilingual speech from 3-second reference audio with a hybrid autoregressive-plus-flow-matching architecture and a new VQ-FSQ tokenizer, achieving 68.4% win rate over ElevenLabs in human evaluations.

citing papers explorer

Showing 1 of 1 citing paper.

  • Voxtral TTS cs.AI · 2026-03-26 · unverdicted · none · ref 16

    Voxtral TTS produces expressive multilingual speech from 3-second reference audio with a hybrid autoregressive-plus-flow-matching architecture and a new VQ-FSQ tokenizer, achieving 68.4% win rate over ElevenLabs in human evaluations.