Voice Activity Detection Optimized by Adaptive Attention Span Transformer
Open Access
- 28 March 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 31238-31243
Abstract
Voice Activity Detection (VAD) is a widely used technique for separating vocal regions from audio signals, with applications in voice language coding, noise reduction, and other domains. While various strategies have been proposed to improve VAD performance, such as ACAM, DCU-10, and Tr-VAD, these approaches often suffer from common limitations, including being unsuitable for long audio and being time-consuming. To address these issues, we propose a new method called AAT-VAD, which integrates an adaptive width attention learning mechanism into the classic transformer framework. Our approach involves extracting Mel-scale Frequency Cepstral Coefficients (MFCC) from the Mel scale frequency domain, adding a masking function to each transformer attention head, and inputting the features processed by the transformer encoder layer into the classifier. Experimental results indicate that our method achieves a 12.8% higher F1-score than DCU-10 and a 0.6% higher F1-score than Tr-VAD under different noise interferences. Furthermore, the average detection cost function (DCF) value of our method is only 14.3% of DCU-10 and 92.4% of Tr-VAD, and the test time of AAT-VAD is only 37.4% of that of Tr-VAD for the same noisy vocal mixed audio.Keywords
This publication has 14 references indexed in Scilit:
- Spiking Deep Residual NetworksIEEE Transactions on Neural Networks and Learning Systems, 2021
- Comparison between Adam, AdaMax and Adam W optimizers to implement a Weather Forecast based on Neural Networks for the Andean city of Quito2021
- An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network2021
- rVAD: An unsupervised segment-based robust voice activity detection methodComputer Speech & Language, 2020
- Convolutional LSTM-based Long-Term Spectrum Prediction for Dynamic Spectrum Access2019
- Voice Activity Detection Using an Adaptive Context Attention ModelIEEE Signal Processing Letters, 2018
- Deep learning for monaural speech separation2014
- The Delta-Phase Spectrum With Application to Voice Activity Detection and Speaker RecognitionIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Bidirectional recurrent neural networksIEEE Transactions on Signal Processing, 1997
- Unit selection in a concatenative speech synthesis system using a large speech database1996