pith. sign in

W2v-bert: Combining contrastive learning and masked language modeling for self-supervised speech pre-training

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

1 Pith paper citing it

fields

cs.SD 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training

cs.SD · 2025-05-23 · unverdicted · novelty 6.0

CosyVoice 3 achieves better content consistency, speaker similarity, and prosody naturalness in zero-shot multilingual speech synthesis by scaling data to one million hours, model size to 1.5 billion parameters, and introducing a supervised multi-task speech tokenizer plus a differentiable reward模型.

citing papers explorer

Showing 1 of 1 citing paper.

  • CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training cs.SD · 2025-05-23 · unverdicted · none · ref 58

    CosyVoice 3 achieves better content consistency, speaker similarity, and prosody naturalness in zero-shot multilingual speech synthesis by scaling data to one million hours, model size to 1.5 billion parameters, and introducing a supervised multi-task speech tokenizer plus a differentiable reward模型.