TransMask: A Compact and Fast Speech Separation Model Based on Transformer
This addresses the computational efficiency bottleneck for deploying speech separation models in real-world applications, though it appears incremental as it builds on existing transformer-based approaches.
The paper tackles the problem of making speech separation models more practical by reducing model size and inference time while maintaining quality, proposing TransMask which achieves over 60% smaller size, more than 2x faster inference, and SDR above 16 on the Librimix benchmark.
Speech separation is an important problem in speech processing, which targets to separate and generate clean speech from a mixed audio containing speech from different speakers. Empowered by the deep learning technologies over sequence-to-sequence domain, recent neural speech separation models are now capable of generating highly clean speech audios. To make these models more practical by reducing the model size and inference time while maintaining high separation quality, we propose a new transformer-based speech separation approach, called TransMask. By fully un-leashing the power of self-attention on long-term dependency exception, we demonstrate the size of TransMask is more than 60% smaller and the inference is more than 2 times faster than state-of-the-art solutions. TransMask fully utilizes the parallelism during inference, and achieves nearly linear inference time within reasonable input audio lengths. It also outperforms existing solutions on output speech audio quality, achieving SDR above 16 over Librimix benchmark.