Rtfs-net: Recurrent Time-frequency Modelling For Efficient Audio-visual Speech Separation

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypegg2023rtfs

Related papers

• Time Domain Audio Visual Speech Separation (2019)14.62
• Tasnet: Time-domain Audio Separation Network For Real-time, Single-channel Speech Separation (2017)20.16
• Conv-tasnet: Surpassing Ideal Time-frequency Magnitude Masking For Speech Separation (2018)24.08
• Effective Low-cost Time-domain Audio Separation Using Globally Attentive Locally Recurrent Networks (2021)10.07
• Audio-visual Speech Separation Based On Joint Feature Representation With Cross-modal Attention (2022)0.00
• Tf-gridnet: Integrating Full- And Sub-band Modeling For Speech Separation (2022)0.00
• Audio-visual Speech Separation In Noisy Environments With A Lightweight Iterative Model (2023)0.00
• Multi-scale Feature Fusion Transformer Network For End-to-end Single Channel Speech Separation (2022)0.00