Improved Separation of Closely-spaced Speakers by Exploiting Auxiliary Direction of Arrival Information within a U-Net Architecture

Abstract

Microphone arrays use spatial diversity for separating concurrent audio sources. Source signals from different directions of arrival (DOAs) are captured with DOAdependent time-delays between the microphones. These can be exploited in the short-time Fourier transform domain to yield time-frequency masks that extract a target signal while suppressing unwanted components. Using deep neural networks (DNNs) for mask estimation has drastically improved separation performance. However, separation of closely spaced sources remains difficult due to their similar inter-microphone time delays. We propose using auxiliary information on source DOAs within the DNN to improve the separation. This can be encoded by the expected phase differences between the microphones. Alternatively, the DNN can learn a suitable input representation on its own when provided with a multi-hot encoding of the DOAs. Experimental results demonstrate the benefit of this information for separating closely spaced sources.

Insights Into Deep Non-Linear Filters for Improved Multi-Channel Speech Enhancement

“…This avoids an implicit far-field assumption and leads to better performance, as we showed in [26]. Similarly, Kindt et al [31] have shown that a learned encoding based on a one-hot encoded angle used as a feature to improve separation of closely spaced speakers is more valuable than a hand-crafted feature based on expected phase differences.…”