RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation
This addresses the problem of efficient and high-quality speech separation for applications like speech recognition, offering a novel approach that outperforms existing time-domain methods.
The paper tackles audio-visual speech separation by proposing RTFS-Net, a time-frequency domain method that uses recurrent modeling and attention-based fusion, achieving state-of-the-art separation quality and inference speed while reducing parameters by 90% and MACs by 83%.
Audio-visual speech separation methods aim to integrate different modalities to generate high-quality separated speech, thereby enhancing the performance of downstream tasks such as speech recognition. Most existing state-of-the-art (SOTA) models operate in the time domain. However, their overly simplistic approach to modeling acoustic features often necessitates larger and more computationally intensive models in order to achieve SOTA performance. In this paper, we present a novel time-frequency domain audio-visual speech separation method: Recurrent Time-Frequency Separation Network (RTFS-Net), which applies its algorithms on the complex time-frequency bins yielded by the Short-Time Fourier Transform. We model and capture the time and frequency dimensions of the audio independently using a multi-layered RNN along each dimension. Furthermore, we introduce a unique attention-based fusion technique for the efficient integration of audio and visual information, and a new mask separation approach that takes advantage of the intrinsic spectral nature of the acoustic features for a clearer separation. RTFS-Net outperforms the prior SOTA method in both inference speed and separation quality while reducing the number of parameters by 90% and MACs by 83%. This is the first time-frequency domain audio-visual speech separation method to outperform all contemporary time-domain counterparts.