7 papers
ReLMCodec: Designing Predictable Speech Tokens from Pre-Quantization Phoneme Structure
Zixiang Wan, Xusheng Yang, Zheng Wang +1
Neural speech codecs face a fundamental tension in the language-model era: tokens that support high-fidelity reconstruction are not necessarily easy for autoregressive models to pr…
FineCombo-TTS: Collaborative and Precise Controllable Speech Synthesis Using Text Descriptions and Reference Speech
Shuoyi Zhou, Yixuan Zhou, Peiji Yang +4
Controllable text-to-speech (TTS) has become a key research focus. However, methods based on either reference speech or text descriptions lack flexibility and precise control, and…
TellWhisper: Tell Whisper Who Speaks When
Yifan Hu, Peiji Yang, Zhisheng Wang +2
Multi-speaker automatic speech recognition (MASR) aims to predict ''who spoke when and what'' from multi-speaker speech, a key technology for multi-party dialogue understanding. Ho…
HPSU: A Benchmark for Human-Level Perception in Real-World Spoken Speech Understanding
Chen Li, Peiji Yang, Yicheng Zhong +5
Recent advances in Speech Large Language Models (Speech LLMs) have led to great progress in speech understanding tasks such as Automatic Speech Recognition (ASR) and Speech Emotion…
Multi-Reward GRPO for Stable and Prosodic Single-Codebook TTS LLMs at Scale
Yicheng Zhong, Peiji Yang, Zhisheng Wang
Recent advances in Large Language Models (LLMs) have transformed text-to-speech (TTS) synthesis, inspiring autoregressive frameworks that represent speech as sequences of discrete…
Optimizing Neural Speech Codec for Low-Bitrate Compression via Multi-Scale Encoding
Peiji Yang, Fengping Wang, Yicheng Zhong +2
Neural speech codecs have demonstrated their ability to compress high-quality speech and audio by converting them into discrete token representations. Most existing methods utilize…