Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
VoiceCraft-X: Unifying Multilingual, Voice-Cloning Speech Synthesis and Speech Editing
Association for Computational Linguistics 2025, Bhat, Vimal (Amazon (United States)), Diwan, Anuj (The University of Texas at Austin), David F. Harwath (The University of Texas at Austin), Huynh, Cong Phuoc, Liu, Zhu (Amazon (United States)), Peng, Puyuan, Sun, Xiaohang, Zheng, Zhisheng (The University of Texas at Austin)
Résumé : We introduce VoiceCraft-X, an autoregressive neural codec language model which unifies multilingual speech editing and zero-shot text-to-speech (TTS) synthesis across 11 languages: English, Mandarin, Korean, Japanese, Spanish, French, German, Dutch, Italian, Portuguese, and Polish. VoiceCraft-X utilizes the Qwen3 large language model for phoneme-free cross-lingual text processing and a novel token reordering mechanism with time-aligned text and speech tokens to handle both tasks as a single sequence generation problem. The model generates high-quality, natural-sounding speech, seamlessly creating new audio or editing existing recordings within one framework. VoiceCraft-X shows robust performance in diverse linguistic settings, even with limited per-language data, underscoring the power of unified autoregressive approaches for advancing complex, real-world multilingual speech applications. Audio samples are available at https://voicecraft-x.github.io/.