Runxuan Yang

15 papers A* 3A 2C 2Journal 8
YearRankTypeTitle / Venue / Authors
2025 A conf
A Fast and Lightweight Model for Causal Audio-Visual Speech Separation.
ECAI
Wendi Sang, Kai Li, Runxuan Yang, Jianqiang Huang, Xiaolin Hu
2025 J jnl
A Fast and Lightweight Model for Causal Audio-Visual Speech Separation.
CoRR
Wendi Sang, Kai Li, Runxuan Yang, Jianqiang Huang, Xiaolin Hu
2025 J jnl
Enhancing Spectrogram Realism in Singing Voice Synthesis via Explicit Bandwidth Extension Prior to Vocoder.
CoRR
Runxuan Yang, Kai Li, Guo Chen, Xiaolin Hu
2025 J jnl
GLM-TTS Technical Report.
CoRR
Jiayan Cui, Zhihan Yang, Naihan Li, Jiankun Tian, Xingyu Ma, Yi Zhang, Guangyu Chen, Runxuan Yang, Yuqing Cheng, Yizhi Zhou, Guochen Yu, Xiaotao Gu, Jie Tang
2025 A conf
SPMamba: Leveraging Long-Sequence Modeling with State Space Models for Speech Separation.
ICME
Kai Li, Guo Chen, Runxuan Yang, Xiaolin Hu
2025 A* conf
SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios.
ICLR
Kai Li, Wendi Sang, Chang Zeng, Runxuan Yang, Guo Chen, Xiaolin Hu
2025 C conf
Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation.
ASRU
Guo Chen, Kai Li, Runxuan Yang, Xiaolin Hu
2025 J jnl
Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation.
CoRR
Guo Chen, Kai Li, Runxuan Yang, Xiaolin Hu
2024 A* conf
IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation.
ICML
Kai Li, Runxuan Yang, Fuchun Sun, Xiaolin Hu
2024 C conf
PhonHuBERT: A Phoneme Transcription Tool for Song Datasets.
ISNN
Amaury Prat, Runxuan Yang, Xiaolin Hu
2024 J jnl
SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios.
CoRR
Kai Li, Wendi Sang, Chang Zeng, Runxuan Yang, Guo Chen, Xiaolin Hu
2023 J jnl
A Fast High-Fidelity Source-Filter Vocoder With Lightweight Neural Modules.
IEEE ACM Trans. Audio Speech Lang. Process.
Runxuan Yang, Yuyang Peng, Xiaolin Hu
2023 A* conf
An efficient encoder-decoder architecture with top-down attention for speech separation.
ICLR
Kai Li, Runxuan Yang, Xiaolin Hu
2023 J jnl
SCANet: A Self- and Cross-Attention Network for Audio-Visual Speech Separation.
CoRR
Kai Li, Runxuan Yang, Xiaolin Hu
2022 J jnl
An efficient encoder-decoder architecture with top-down attention for speech separation.
CoRR
Kai Li, Runxuan Yang, Xiaolin Hu