A Neural Beamspace-Domain Filter for Real-Time Multi-Channel Speech Enhancement
Open Access
Abstract
Most deep-learning-based multi-channel speech enhancement methods focus on designing a set of beamforming coefficients, to directly filter the low signal-to-noise ratio signals received by microphones, which hinders the performance of these approaches. To handle these problems, this paper designs a causal neural filter that fully exploits the spectro-temporal-spatial information in the beamspace domain. Specifically, multiple beams are designed to steer towards all directions, using a parameterized super-directive beamformer in the first stage. After that, a deep-learning-based filter is learned by, simultaneously, modeling the spectro-temporal-spatial discriminability of the speech and the interference, so as to extract the desired speech, coarsely, in the second stage. Finally, to further suppress the interference components, especially at low frequencies, a residual estimation module is adopted, to refine the output of the second stage. Experimental results demonstrate that the proposed approach outperforms many state-of-the-art (SOTA) multi-channel methods, on the generated multi-channel speech dataset based on the DNS-Challenge dataset.Keywords
All Related Versions
Funding Information
- National Environmental Protection Engineering and Technology Center for Road Traffic Noise Control (F20221018)
This publication has 40 references indexed in Scilit:
- Neural Spatial Filter: Target Speaker Speech Separation Assisted with Directional Information2019
- Multi-Channel Speech Enhancement Using Time-Domain Convolutional Denoising Autoencoder2019
- Supervised Speech Separation Based on Deep Learning: An OverviewIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2018
- An Algorithm for Predicting the Intelligibility of Speech Masked by Modulated Noise MaskersIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016
- Reduced-Order Robust Superdirective Beamforming With Uniform Linear Microphone ArraysIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016
- Blind Speech Separation2007
- Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systemsSpeech Communication, 1993
- Speech database development at MIT: Timit and beyondSpeech Communication, 1990
- Maximum directivity proof for three-dimensional arraysThe Journal of the Acoustical Society of America, 1987
- Image method for efficiently simulating small-room acousticsThe Journal of the Acoustical Society of America, 1979