We present M5-TTS, a compact text-to-speech system supporting multilingual and Chinese multidialect synthesis, zero-shot voice cloning, speaker-specific multilingual generation, and CPU streaming. Its 50M-parameter language model, excluding the speech codec, combines a temporal backbone with a local multi-token predict...
Wen-Hao Li, Jing-Bin Hu, Sheng-Ming Ling et al.· 0 citations
Recent advances in speech generation are shifting toward context-aware, multi-turn, and multi-speaker synthesis. While these capabilities are in high demand for applications such as audiobook and audio drama production, evaluation has not kept pace with these advances. Beyond traditional zero-shot Text-to-Speech (TTS),...
Jing-Bin Hu, Zi-Tao Yang, Xiao-Ge Peng et al.· 0 citations
Nonverbal vocalizations (NVVs), such as laughter and sighs, convey meaning alongside words. NVV-aware speech systems must recognize and generate these events while preserving lexical accuracy and perceptual quality. Yet differences in annotation, resources, and evaluation complicate comparisons, and aggregate scores ca...
Liu-Meng Xue, Yuang Cao, Jing-Bin Hu et al.· 0 citations
Continuous latent representations underlie recent diffusion-based lyrics-to-song and text-to-music systems, yet aligning lyric conditions with these latents remains difficult: existing systems resort to generator-side machinery such as sentence-level timestamps, auxiliary alignment objectives, or semi-autoregressive de...
Guo-Bin Ma, Yue-Peng Jiang, Da-Ke Guo et al.· 0 citations
StreamTN is proposed, a lightweight LLM-based Chinese streaming TN model that employs a dual-track streaming framework in which input tokens and output tokens are processed on two parallel tracks, enabling low-latency real-time inference without complex prompting.
Wen-Hao Li, Jin-Rui Liang, Hao-Yu Zhang et al.· 0 citations
MuSeC is proposed, a music semantic codec that factorizes semantic and acoustic content directly from mixed signals without source separation that preserves information required for high-fidelity reconstruction while producing more LM-friendly discrete units.
Hua-Kang Chen, Guo-Bin Ma, Yue-Peng Jiang et al.· 0 citations
SemBridge is proposed, a training-only semantic-token anchoring framework for continuous-latent autoregressive speech generation and demonstrates that explicit semantic-token supervision for autoregressive state learning is an effective and general direction for continuous speech generation.
Han-Ke Xie, Haopeng Lin, J. Qian et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.