TasNet: time-domain audio separation network for real-time, single-channel speech separation

Abstract

Robust speech processing in multi-talker environments requires effective speech separation. Recent deep learning systems have made significant progress toward solving this problem, yet it remains challenging particularly in real-time, short latency applications. Most methods attempt to construct a mask for each source in time-frequency representation of the mixture signal which is not necessarily an optimal representation for speech separation. In addition, time-frequency decomposition results in inherent problems such as phase/magnitude decoupling and long time window which is required to achieve sufficient frequency resolution. We propose Time-domain Audio Separation Network (TasNet) to overcome these limitations. We directly model the signal in the time-domain using an encoder-decoder framework and perform the source separation on nonnegative encoder outputs. This method removes the frequency decomposition step and reduces the separation problem to estimation of source masks on encoder outputs which is then synthesized by the decoder. Our system outperforms the current state-of-the-art causal and noncausal speech separation algorithms, reduces the computational cost of speech separation, and significantly reduces the minimum required latency of the output. This makes TasNet suitable for applications where low-power, real-time implementation is desirable such as in hearable and telecommunication devices.

Camera ready version for ICASSP 2018, Calgary, Canada

References in corpus (4)

• WaveNet: A Generative Model for Raw Audio
• Deep attractor network for single-microphone speaker separation
• SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
• Speaker-independent Speech Separation with Deep Attractor Network

Cited by in corpus (7)

• Look Once to Hear: Target Speech Hearing with Noisy Examples
• Mean absorption estimation from room impulse responses using virtually supervised learning
• Attention is All You Need in Speech Separation
• Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective
• A comparison of handcrafted, parameterized, and learnable features for speech separation
• FurcaNeXt: End-to-end monaural speech separation with dynamic gated dilated temporal convolutional networks
• Phase Aware Speech Enhancement using Realisation of Complex-valued LSTM