End-to-end Domain-adversarial Voice Activity Detection

Abstract

Voice activity detection is the task of detecting speech regions in a given audio stream or recording. First, we design a neural network combining trainable filters and recurrent layers to tackle voice activity detection directly from the waveform. Experiments on the challenging DIHARD dataset show that the proposed end-to-end model reaches state-of-the-art performance and outperforms a variant where trainable filters are replaced by standard cepstral coefficients. Our second contribution aims at making the proposed voice activity detection model robust to domain mismatch. To that end, a domain classification branch is added to the network and trained in an adversarial manner. The same DIHARD dataset, drawn from 11 different domains is used for evaluation under two scenarios. In the in-domain scenario where the training and test sets cover the exact same domains, we show that the domain-adversarial approach does not degrade performance of the proposed end-to-end model. In the out-domai

Stats

• citations23
• S2 citations—
• github stars0
• HF likes0
• heat score10.35
• arxiv keylavechin2019end

Related papers

• Adversarial Multi-task Deep Learning For Noise-robust Voice Activity Detection With Low Algorithmic Delay (2022)2.26
• Speech Enhancement Aided End-to-end Multi-task Learning For Voice Activity Detection (2020)11.49
• Attentive Adversarial Learning For Domain-invariant Training (2019)6.77
• Self-adaptive Soft Voice Activity Detection Using Deep Neural Networks For Robust Speaker Verification (2019)6.77
• An End-to-end Architecture For Keyword Spotting And Voice Activity Detection (2016)0.00
• Temporarily-aware Context Modelling Using Generative Adversarial Networks For Speech Activity Detection (2020)7.50
• Speaker Verification Using End-to-end Adversarial Language Adaptation (2018)11.19
• Target Speaker Voice Activity Detection With Transformers And Its Integration With End-to-end Neural Diarization (2022)10.48