A Multi-Phase Gammatone Filterbank for Speech Separation via TasNet

Abstract

In this work, we investigate if the learned encoder of the end-to-end convolutional time domain audio separation network (Conv-TasNet) is the key to its recent success, or if the encoder can just as well be replaced by a deterministic hand-crafted filterbank. Motivated by the resemblance of the trained encoder of Conv-TasNet to auditory filterbanks, we propose to employ a deterministic gammatone filterbank. In contrast to a common gammatone filterbank, our filters are restricted to 2 ms length to allow for low-latency processing. Inspired by the encoder learned by Conv-TasNet, in addition to the logarithmically spaced filters, the proposed filterbank holds multiple gammatone filters at the same center frequency with varying phase shifts. We show that replacing the learned encoder with our proposed multi-phase gammatone filterbank (MP-GTF) even leads to a scale-invariant source-to-noise ratio (SI-SNR) improvement of 0.7 dB. Furthermore, in contrast to using the learned encoder we show that the number of filters can be reduced from 512 to 128 without loss of performance.

arXiv commentAccepted at ICASSP 2020

References in corpus (3)

• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
• Deep attractor network for single-microphone speaker separation
• End-to-end training of time domain audio separation and recognition

Cited by in corpus (12)

• Neural Target Speech Extraction: An Overview
• Asteroid: the PyTorch-based audio source separation toolkit for researchers
• Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation
• Phase-Aware Deep Speech Enhancement: It's All About The Frame Length
• Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes
• A comparison of handcrafted, parameterized, and learnable features for speech separation
• Multi-channel target speech extraction with channel decorrelation and target speaker adaptation
• Deep Ad-hoc Beamforming
• On permutation invariant training for speech source separation
• Dissecting Performance Degradation in Audio Source Separation under Sampling Frequency Mismatch
• Attention-based scaling adaptation for target speech extraction
• Phase recovery with Bregman divergences for audio source separation