Current browse context:
eess.AS
Change to browse by:
References & Citations
Electrical Engineering and Systems Science > Audio and Speech Processing
Title: VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild
(Submitted on 25 Mar 2024 (v1), last revised 19 Apr 2024 (this version, v2))
Abstract: We introduce VoiceCraft, a token infilling neural codec language model, that achieves state-of-the-art performance on both speech editing and zero-shot text-to-speech (TTS) on audiobooks, internet videos, and podcasts. VoiceCraft employs a Transformer decoder architecture and introduces a token rearrangement procedure that combines causal masking and delayed stacking to enable generation within an existing sequence. On speech editing tasks, VoiceCraft produces edited speech that is nearly indistinguishable from unedited recordings in terms of naturalness, as evaluated by humans; for zero-shot TTS, our model outperforms prior SotA models including VALLE and the popular commercial model XTTS-v2. Crucially, the models are evaluated on challenging and realistic datasets, that consist of diverse accents, speaking styles, recording conditions, and background noise and music, and our model performs consistently well compared to other models and real recordings. In particular, for speech editing evaluation, we introduce a high quality, challenging, and realistic dataset named RealEdit. We encourage readers to listen to the demos at this https URL
Submission history
From: Puyuan Peng [view email][v1] Mon, 25 Mar 2024 17:38:32 GMT (9071kb,D)
[v2] Fri, 19 Apr 2024 19:33:08 GMT (9073kb,D)
Link back to: arXiv, form interface, contact.