Zero-shot text-to-speech (TTS) can clone a speaker's voice from a short audio prompt, yet most TTS systems still require the audio prompt transcript during inference. This dependency prevents cross-lingual voice cloning when the audio prompt transcript is unavailable, particularly for unseen languages. Cross-Lingual F5...
Qingyun Liu, Rixi Xu, Yu-Shen Chen et al.· 0 citations
AuK, an open-source foundational model that unifies speech generation and editing through a common interface of natural-language instructions and audio context, is introduced and leading performance on zero-shot and instruction-controlled speech generation and general instruction-guided editing is demonstrated.
Zi-Yang Ma, Zhi-Kang Niu, Wen-Ming Tu et al.· 3 citations· ⚡1
X-Translator is presented, a low-cost modular cascaded S2ST system that combines streaming ASR, machine translation, and prompt-conditioned TTS through a session-level runtime controller that provides an open platform for understanding the practical trade-offs of deployment-oriented S2ST.
Yuxiang Zhao, Yichi Zhang, Yanjie An et al.· 0 citations
This work proposes a novel two-stage framework that protects both linguistic content and acoustic identity while maintaining usability and introduces F3-VA, a flow-matching-based anonymization framework with a three-stage design that produces diverse and distinct anonymized speakers.
Yunchong Xiao, Yuxiang Zhao, Ziyang Ma et al.· IEEE Transactions on Audio,...· 1 citation
The first large-scale speech dialogue dataset engineered for multiple fine-grained speech style control, UltraVoice, demonstrates substantial gains in core understanding, reasoning, and conversational abilities, and its utility extends to training controllable Text-to-Speech (TTS) models.
Wen-Ming Tu, Guanrou Yang, Rui-Qi Yan et al.· arXiv.org· 3 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
