Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Zhiwei Lin

Zhiwei Lin

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Sound×2Audio and Speech Processing×2

Frequent co-authors

Jun Chen1×
Boshi Tang1×
Weihao Wu1×
Yang Jing1×
Yaolong Ju1×
Fan Fan1×

Research Timeline

2026
Balancing ASR and diarization in end-to-end LLMs for multi-talker speech recognition

The paper proposes strategies to efficiently train an LLM-based system for multi-talker speech recognition with limited data.

Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Model

This paper introduces Diff-Symbo, a method for generating high-quality, diverse, and long-duration symbolic music using a latent diffusion model and a comprehensive text-symbolic music dataset.

Highlighted terms show continued research focus across papers

Papers

cs.SDeess.ASEmpiricalRecentAug 5, 2026

Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Model

Zhiwei Lin, Jun Chen, Boshi Tang, Weihao Wu +4 more

This paper introduces Diff-Symbo, a method for generating high-quality, diverse, and long-duration symbolic music using a latent diffusion model and a comprehensive text-symbolic music dataset.

View →
eess.AScs.SDEmpirical
Recent
Jun 11, 2026

Balancing ASR and diarization in end-to-end LLMs for multi-talker speech recognition

Naijun Zheng, Yuke Lin, Sanli Tian, Mengtian Li +3 more

The paper proposes strategies to efficiently train an LLM-based system for multi-talker speech recognition with limited data.

View →