collaborators

5 papers

cs.CL2025

MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance

Xingjian Zhao, Zhe Xu, Qinyuan Cheng +20

Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits exp…

cs.LG2025

Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance

Luozhijie Jin, Zijie Qiu, Jie Liu +5

Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex…

eess.AS2025

CodecBench: A Comprehensive Benchmark for Acoustic and Semantic Evaluation

Ruifan Deng, Yitian Gong, Qinghui Gao +5

With the rise of multimodal large language models (LLMs), audio codec plays an increasingly vital role in encoding audio into discrete tokens, enabling integration of audio into te…

cs.SD2025

XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs

Yitian Gong, Luozhijie Jin, Ruifan Deng +6

Speech codecs serve as bridges between speech signals and large language models. An ideal codec for speech language models should not only preserve acoustic information but also ca…

cs.CL2025

From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models

Yurui Dong, Luozhijie Jin, Yao Yang +3

Purpose: Emotion is a fundamental component of human communication, shaping understanding, trust, and engagement across domains such as education, healthcare, and mental health. Wh…