collaborators

7 papers

eess.AS2026

HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech

Sihang Nie, Xiaofen Xing, Rui Xing +5

Recently, Large Language Model (LLM)-based Text-to-Speech (TTS) models have achieved remarkable naturalness. However, the standard Supervised Fine-Tuning paradigm often converges t…

eess.AS2026

HD-PPT: Hierarchical Decoding of Content- and Prompt-Preference Tokens for Instruction-based TTS

Sihang Nie, Xiaofen Xing, Jingyuan Xing +2

Large Language Model (LLM)-based Text-to-Speech (TTS) models have already reached a high degree of naturalness. However, the precision control of TTS inference is still challenging…

cs.SD2025

BridgeCode: A Dual Speech Representation Paradigm for Autoregressive Zero-Shot Text-to-Speech Synthesis

Jingyuan Xing, Mingru Yang, Zhipeng Li +2

Autoregressive (AR) frameworks have recently achieved remarkable progress in zero-shot text-to-speech (TTS) by leveraging discrete speech tokens and large language model techniques…

cs.SD2025

MNV-17: A High-Quality Performative Mandarin Dataset for Nonverbal Vocalization Recognition in Speech

Jialong Mai, Jinxin Ji, Xiaofen Xing +4

Mainstream Automatic Speech Recognition (ASR) systems excel at transcribing lexical content, but largely fail to recognize nonverbal vocalizations (NVs) embedded in speech, such as…

cs.CL2025

Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation

Jialong Mai, Xiaofen Xing, Yawei Li +4

Recent research has focused on applying speech large language model (SLLM) to improve speech emotion recognition (SER). However, the inherently high frame rate in speech modality s…

eess.AS2025

Parallel GPT: Harmonizing the Independence and Interdependence of Acoustic and Semantic Information for Zero-Shot Text-to-Speech

Jingyuan Xing, Zhipeng Li, Jialong Mai +2

Advances in speech representation and large language models have enhanced zero-shot text-to-speech (TTS) performance. However, existing zero-shot TTS models face challenges in capt…