A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments
This addresses speech separation for noisy and reverberant settings, which is an incremental improvement over existing methods.
The paper tackles speech separation in noisy and reverberant environments by proposing a multi-stage triple-path method that decouples the problem into denoising, separation, and de-reverberation, improving performance with minimal parameter increase.
In noisy and reverberant environments, the performance of deep learning-based speech separation methods drops dramatically because previous methods are not designed and optimized for such situations. To address this issue, we propose a multi-stage end-to-end learning method that decouples the difficult speech separation problem in noisy and reverberant environments into three sub-problems: speech denoising, separation, and de-reverberation. The probability and speed of searching for the optimal solution of the speech separation model are improved by reducing the solution space. Moreover, since the channel information of the audio sequence in the time domain is crucial for speech separation, we propose a triple-path structure capable of modeling the channel dimension of audio sequences. Experimental results show that the proposed multi-stage triple-path method can improve the performance of speech separation models at the cost of little model parameter increment.