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

Haolong Zheng

2 indexed papers

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

Publications per year

2
26

Top categories

Audio and Speech Processing×2NLP×1

Frequent co-authors

Yujie Tu1×
Yifan Yang1×
Tianrui Wang1×
Yanqiao Zhu1×
Guodong Lin1×
Mingchen Shao1×

Research Timeline

2026
SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors

SALSA is a lightweight adaptation method that learns layer-wise steering vectors to significantly improve the performance of speech-aware LLMs on out-of-domain speech tasks.

GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark

The paper introduces GigaSpeechBench, a comprehensive multilingual and multidimensional ASR & AST benchmark with 680 hours of human-annotated speech, featuring 12 low-resource languages, 6 Chinese dialects, 6 English accents, dense terminology, older adult and child speech, and human-annotated translations.

Highlighted terms show continued research focus across papers

Papers

eess.ASEmpirical