Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay

Claus Meyer Larsen, Peter Koch, Zheng-Hua Tan*

*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review


Voice Activity Detection (VAD) is an important pre-processing step in a wide variety of speech processing systems. VAD should in a practical application be able to detect speech in both noisy and noise-free environments, while not introducing significant latency. In this work we propose using an adversarial multi-task learning method when training a supervised VAD. The method has been applied to the state-of-the-art VAD Waveform-based Voice Activity Detection. Additionally the performance of the VAD is investigated under different algorithmic delays, which is an important factor in latency. Introducing adversarial multi-task learning to the model is observed to increase performance in terms of Area Under Curve (AUC), particularly in noisy environments, while the performance is not degraded at higher SNR levels. The adversarial multi-task learning is only applied in the training phase and thus introduces no additional
cost in testing. Furthermore the correlation between performance and algorithmic delays is investigated, and it is observed that the VAD performance degradation is only moderate when lowering the algorithmic delay from 398 ms to 23 ms. Index Terms: Voice Activity Detection, adversarial multi-task learning, algorithmic delay, deep learning, noise robustness.
Original languageEnglish
Title of host publicationInterspeech 2022
Publication date2022
Publication statusPublished - 2022
EventInterspeech 2022 - Incheon, Korea, Republic of
Duration: 18 Sept 202222 Sept 2022


ConferenceInterspeech 2022
Country/TerritoryKorea, Republic of
SeriesProceedings of the International Conference on Spoken Language Processing


Dive into the research topics of 'Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay'. Together they form a unique fingerprint.

Cite this