Evaluation of Deep-Learning-Based Voice Activity Detectors and Room Impulse Response Models in Reverberant Environments

by   Amir Ivry, et al.

State-of-the-art deep-learning-based voice activity detectors (VADs) are often trained with anechoic data. However, real acoustic environments are generally reverberant, which causes the performance to significantly deteriorate. To mitigate this mismatch between training data and real data, we simulate an augmented training set that contains nearly five million utterances. This extension comprises of anechoic utterances and their reverberant modifications, generated by convolutions of the anechoic utterances with a variety of room impulse responses (RIRs). We consider five different models to generate RIRs, and five different VADs that are trained with the augmented training set. We test all trained systems in three different real reverberant environments. Experimental results show 20% increase on average in accuracy, precision and recall for all detectors and response models, compared to anechoic training. Furthermore, one of the RIR models consistently yields better performance than the other models, for all the tested VADs. Additionally, one of the VADs consistently outperformed the other VADs in all experiments.


IR-GAN: Room Impulse Response Generator for Speech Augmentation

We present a Generative Adversarial Network (GAN) based room impulse res...

Training Strategies for Own Voice Reconstruction in Hearing Protection Devices using an In-ear Microphone

In-ear microphones in hearing protection devices can be utilized to capt...

Semi-supervised voice conversion with amortized variational inference

In this work we introduce a semi-supervised approach to the voice conver...

Deep Learning-based Stress Determinator for Mouse Psychiatric Analysis using Hippocampus Activity

Decoding neurons to extract information from transmission and employ the...

Efficient Training Data Generation for Phase-Based DOA Estimation

Deep learning (DL) based direction of arrival (DOA) estimation is an act...

Towards Testing of Deep Learning Systems with Training Set Reduction

Testing the implementation of deep learning systems and their training r...

Ensemble of ACCDOA- and EINV2-based Systems with D3Nets and Impulse Response Simulation for Sound Event Localization and Detection

This report describes our systems submitted to the DCASE2021 challenge t...