Machine learning

Chemistry

Speech enhancement

Microphone

Filter (signal processing)

Economics

Biochemistry

Telecommunications

Physics

Mutual fund separation theorem

Permutation (music)

Mathematics

Mathematical physics

Beamforming

Gene

Acoustics

Invariant (physics)

Computer science

Sound pressure

Financial economics

Algorithm

Separation (statistics)

Microphone array

Portfolio

Speech recognition

Computer vision

Robustness (evolution)

An important problem in ad-hoc microphone speech separation is how to guarantee the robustness of a system with respect to the locations and numbers of microphones. The former requires the system to be invariant to different indexing of the microphones with the same locations, while the latter requires the system to be able to process inputs with varying dimensions. Conventional optimization-based beamforming techniques satisfy these requirements by definition, while for deep learning-based end-to-end systems those constraints are not fully addressed. In this paper, we propose transform-average-concatenate (TAC), a simple design paradigm for channel permutation and number invariant multi-channel speech separation. Based on the filter-and-sum network (FaSNet), a recently proposed end-to-end time-domain beamforming system, we show how TAC significantly improves the separation performance across various numbers of microphones in noisy reverberant separation tasks with ad-hoc arrays. Moreover, we show that TAC also significantly improves the separation performance with fixed geometry array configuration, further proving the effectiveness of the proposed paradigm in the general problem of multi-microphone speech separation.

End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation