6 papers
Beyond Reconstruction: Full-Context Generative DiT for Music Generation
Yunjia Li, Menglin Wu, Junyu Dai +13
Hybrid music generators combine the long-range planning of an autoregressive language model with the fidelity of a diffusion- or flow-based acoustic renderer. Yet renderers are tra…
X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System
Yuxiang Zhao, Yichi Zhang, Yanjie An +10
Real-time speech-to-speech translation (S2ST) systems must balance translation quality, latency, speech naturalness, and speaker consistency. Publicly documented S2ST systems have…
OpenSTBench: Beyond Semantic Evaluation for Speech Translation
Yanjie An, Yuxiang Zhao, Yichi Zhang +5
Speech translation systems increasingly span speech-to-text translation (S2TT), speech-to-speech translation (S2ST), offline translation, and streaming generation, producing output…
X-VC: Zero-shot Streaming Voice Conversion in Codec Space
Qixi Zheng, Yuxiang Zhao, Tianrui Wang +7
Zero-shot voice conversion (VC) aims to convert a source utterance into the voice of an unseen target speaker while preserving its linguistic content. Although recent systems have…
Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
Qixi Zheng, Yushen Chen, Zhikang Niu +4
Flow-matching-based text-to-speech (TTS) models, such as Voicebox, E2 TTS, and F5-TTS, have attracted significant attention in recent years. These models require multiple sampling…
Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
Xinsheng Wang, Mingqi Jiang, Ziyang Ma +22
Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis. However, existing foundation models rely on multi-…