# Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction

Source: [Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction](<https://www.sota2.com/research/paper/68fa6f641e209131cea4541f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:58.871Z

Authors: Mohan Shi, Yuchun Shu, Lingyun Zuo, Qian Chen, Shiliang Zhang, Jie Zhang, Li-Rong Dai

Published: 2023-05-21T13:02:53.000Z

## Abstract

For speech interaction, voice activity detection (VAD) is often used as a front-end. However, traditional VAD algorithms usually need to wait for a continuous tail silence to reach a preset maximum duration before segmentation, resulting in a large latency that affects user experience. In this paper, we propose a novel semantic VAD for low-latency segmentation. Different from existing methods, a frame-level punctuation prediction task is added to the semantic VAD, and the artificial endpoint is included in the classification category in addition to the often-used speech presence and absence. To enhance the semantic information of the model, we also incorporate an automatic speech recognition (ASR) related semantic loss. Evaluations on an internal dataset show that the proposed method can reduce the average latency by 53.3% without significant deterioration of character error rate in the back-end ASR compared to the traditional VAD approach.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2305.12450>)

[PDF](<https://arxiv.org/pdf/2305.12450.pdf>)
