7 papers
Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization
Peijie Chen, Zhuanling Zha, Zhipeng Nie +8
In current zero-shot text-to-speech systems, conventional semantic tokenizers are typically optimized using supervised automatic speech recognition or self-supervised learning obje…
MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning
Weijie Wu, Junbo Li, Lin Li +2
With the development of audio large language models (AudioLLMs), audio captioning needs to move from brief descriptions toward open-ended and fine-grained free-form descriptions. E…
SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations
Peijie Chen, Wenhao Guan, Weijie Wu +7
Zero-shot text-to-speech (TTS) relies on robust speech representations. However, current speech tokenizers face a fundamental trade-off: acoustic codecs preserve high-fidelity audi…
SyncVoice: Simple and Effective Automatic Video Dubbing with Vision-Augmented TTS
Kaidi Wang, Yi He, Wenhao Guan +9
Automatic video dubbing aims to generate high-fidelity speech that is temporally aligned with visual content. However, existing methods still suffer from limited speech naturalness…
Phoenix-VAD: Streaming Semantic Endpoint Detection for Full-Duplex Speech Interaction
Weijie Wu, Wenhao Guan, Kaidi Wang +6
Spoken dialogue models have significantly advanced intelligent human-computer interaction, yet they lack a plug-and-play full-duplex prediction module for semantic endpoint detecti…
DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec
Peijie Chen, Wenhao Guan, Kaidi Wang +4
Neural speech codecs are essential for advancing text-to-speech (TTS) systems. With the recent success of large language models in text generation, developing high-quality speech t…
Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversion
Kaidi Wang, Wenhao Guan, Ziyue Jiang +5
Currently, zero-shot voice conversion systems are capable of synthesizing the voice of unseen speakers. However, most existing approaches struggle to accurately replicate the speak…