activity
20242026
collaborators

10 papers

eess.AS2026

GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model

Guanrou Yang, Tian Tan, Qian Chen +8

Reinforcement learning for flow-matching text-to-speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE…

eess.AS2026

WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling

Guanrou Yang, Tian Tan, Qian Chen +12

Integrating speech understanding and generation is a pivotal step toward building unified speech models. However, the different representations required for these two tasks current…

cs.SD2026

RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS

Cong Wang, Changfeng Gao, Yang Xiang +7

Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularl…

cs.SD2026

Eliminating stability hallucinations in llm-based tts models via attention guidance

ShiMing Wang, ZhiHao Du, Yang Xiang +6

This paper focuses on resolving stability hallucinations (e.g., repetitive or omitted speech) in LLM-based Text-to-Speech (TTS) models by improving and leveraging the attention mec…

cs.CL2025

DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations

Chao-Hong Tan, Qian Chen, Wen Wang +14

Recent studies on end-to-end (E2E) speech generation with large language models (LLMs) have attracted significant community attention, with multiple works extending text-based LLMs…

cs.CL2025

Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modeling

Yue Gu, Zhihao Du, Ying Shi +3

Recently, cross-attention-based contextual automatic speech recognition (ASR) models have made notable advancements in recognizing personalized biasing phrases. However, the effect…