Microphone Array Signal Processing and Deep Learning for Speech Enhancement
arXiv:2501.07215 · doi:10.1109/MSP.2024.3451653
Abstract
Multi-channel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and non-target or noise sources for signal enhancement. However, the textbook solutions for optimal data-dependent spatial filtering rest on the knowledge of second-order statistical moments of the signals, which have traditionally been difficult to acquire. In this contribution, we compare model-based, purely data-driven, and hybrid approaches to parameter estimation and filtering, where the latter tries to combine the benefits of model-based signal processing and data-driven deep learning to overcome their individual deficiencies. We illustrate the underlying design principles with examples from noise reduction, source separation, and dereverberation.
Accepted for IEEE Signal Processing Magazine
References in corpus (5)
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenario
- Insights Into Deep Non-linear Filters for Improved Multi-channel Speech Enhancement
- Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information
- Blind and neural network-guided convolutional beamformer for joint denoising, dereverberation, and source separation