Open AccessVoice activity detection in noisy conditions using tiny convolutional neural network
Author(s) -
Г. С. Вашкевич,
И. С. Азаров
Publication year - 2020
Publication title -
informatika
Language(s) - English
Resource type - Journals
eISSN - 2617-6963
pISSN - 1816-0301
DOI - 10.37661/1816-0301-2020-17-2-36-43
Subject(s) - computer science , convolutional neural network , voice activity detection , speech recognition , redundancy (engineering) , noise (video) , activity detection , artificial intelligence , speech processing , image (mathematics) , operating system
The paper investigates the problem of voice activity detection from a noisy sound signal. An extremely compact convolutional neural network is proposed. The model has only 385 trainable parameters. Proposed model doesn’t require a lot of computational resources that allows to use it as part of the “internet of things” concept for compact low power devices. At the same time the model provides state of the art results in voice activity detection in terms of detection accuracy. The properties of the model are achieved by using a special convolutional layer that considers the harmonic structure of vocal speech. This layer also eliminates redundancy of the model because it has invariance to changes of fundamental frequency. The model performance is evaluated in various noise conditions with different signal-to-noise ratios. The results show that the proposed model provides higher accuracy compared to voice activity detection model from the WebRTC framework by Google.