English

Advancing VAD Systems Based on Multi-Task Learning with Improved Model Structures

Sound 2023-12-25 v1 Audio and Speech Processing

Abstract

In a speech recognition system, voice activity detection (VAD) is a crucial frontend module. Addressing the issues of poor noise robustness in traditional binary VAD systems based on DFSMN, the paper further proposes semantic VAD based on multi-task learning with improved models for real-time and offline systems, to meet specific application requirements. Evaluations on internal datasets show that, compared to the real-time VAD system based on DFSMN, the real-time semantic VAD system based on RWKV achieves relative decreases in CER of 7.0\%, DCF of 26.1\% and relative improvement in NRR of 19.2\%. Similarly, when compared to the offline VAD system based on DFSMN, the offline VAD system based on SAN-M demonstrates relative decreases in CER of 4.4\%, DCF of 18.6\% and relative improvement in NRR of 3.5\%.

Keywords

Cite

@article{arxiv.2312.14860,
  title  = {Advancing VAD Systems Based on Multi-Task Learning with Improved Model Structures},
  author = {Lingyun Zuo and Keyu An and Shiliang Zhang and Zhijie Yan},
  journal= {arXiv preprint arXiv:2312.14860},
  year   = {2023}
}
R2 v1 2026-06-28T14:00:08.156Z