Enhancing End-to-End Multi-channel Speech Separation via Spatial Feature Learning

Understand

Hand-crafted spatial features (e.g., inter-channel phase difference, IPD) play a fundamental role in recent deep learning based multi-channel speech separation (MCSS) methods.

• However, these manually designed spatial features are hard to incorporate into the end-to-end optimized MCSS framework.
• In this work, we propose an integrated architecture for learning spatial features directly from the multi-channel speech waveforms within an end-to-end speech separation framework.
• In this architecture, time-domain filters spanning signal channels are trained to perform adaptive spatial filtering.