Divide and Conquer: A Deep CASA Approach to Talker-independent Monaural Speaker Separation

Abstract

We address talker-independent monaural speaker separation from the perspectives of deep learning and computational auditory scene analysis (CASA). Specifically, we decompose the multi-speaker separation task into the stages of simultaneous grouping and sequential grouping. Simultaneous grouping is first performed in each time frame by separating the spectra of different speakers with a permutation-invariantly trained neural network. In the second stage, the frame-level separated spectra are sequentially grouped to different speakers by a clustering network. The proposed deep CASA approach optimizes frame-level separation and speaker tracking in turn, and produces excellent results for both objectives. Experimental results on the benchmark WSJ0-2mix database show that the new approach achieves the state-of-the-art results with a modest model size.

arXiv comment10 pages, 5 figures

References in corpus (7)

• Improving neural networks by preventing co-adaptation of feature detectors
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
• Regularizing and Optimizing LSTM Language Models
• Speaker-independent Speech Separation with Deep Attractor Network
• Recurrent Dropout without Memory Loss
• Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective

Cited by in corpus (4)

• Two-Step Sound Source Separation: Training on Learned Latent Targets
• Compute and memory efficient universal sound source separation
• Deep Attention Fusion Feature for Speech Separation with End-to-End Post-filter Method
• Mask-dependent Phase Estimation for Monaural Speaker Separation