Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation

TL;DR

Conv-TasNet is an end-to-end time-domain speech separation network that outperforms traditional time-frequency masking methods and ideal masks, with lower latency and smaller model size, suitable for real-time applications.

Contribution

The paper introduces Conv-TasNet, a novel fully-convolutional time-domain network that surpasses previous methods and ideal masks in speech separation accuracy and efficiency.

Findings

Outperforms previous time-frequency masking methods in separation quality.

Surpasses ideal time-frequency magnitude masks in objective and subjective evaluations.

Has smaller model size and shorter latency, enabling real-time processing.

Abstract

Single-channel, speaker-independent speech separation methods have recently seen great progress. However, the accuracy, latency, and computational cost of such methods remain insufficient. The majority of the previous methods have formulated the separation problem through the time-frequency representation of the mixed signal, which has several drawbacks, including the decoupling of the phase and magnitude of the signal, the suboptimality of time-frequency representation for speech separation, and the long latency in calculating the spectrograms. To address these shortcomings, we propose a fully-convolutional time-domain audio separation network (Conv-TasNet), a deep learning framework for end-to-end time-domain speech separation. Conv-TasNet uses a linear encoder to generate a representation of the speech waveform optimized for separating individual speakers. Speaker separation is achieved by applying a set of weighting functions (masks) to the encoder output. The modified encoder representations are then inverted back to the waveforms using a linear decoder. The masks are found using a temporal convolutional network (TCN) consisting of stacked 1-D dilated convolutional blocks, which allows the network to model the long-term dependencies of the speech signal while maintaining a small model size. The proposed Conv-TasNet system significantly outperforms previous time-frequency masking methods in separating two- and three-speaker mixtures. Additionally, Conv-TasNet surpasses several ideal time-frequency magnitude masks in two-speaker speech separation as evaluated by both objective distortion measures and subjective quality assessment by human listeners. Finally, Conv-TasNet has a significantly smaller model size and a shorter minimum latency, making it a suitable solution for both offline and real-time speech separation applications.