Tiny-sepformer: A Tiny Time-domain Transformer Network For Speech Separation

Abstract

Time-domain Transformer neural networks have proven their superiority in speech separation tasks. However, these models usually have a large number of network parameters, thus often encountering the problem of GPU memory explosion. In this paper, we proposed Tiny-Sepformer, a tiny version of Transformer network for speech separation. We present two techniques to reduce the model parameters and memory consumption: (1) Convolution-Attention (CA) block, spliting the vanilla Transformer to two paths, multi-head attention and 1D depthwise separable convolution, (2) parameter sharing, sharing the layer parameters within the CA block. In our experiments, Tiny-Sepformer could greatly reduce the model size, and achieves comparable separation performance with vanilla Sepformer on WSJ0-2/3Mix datasets.

Stats

• citations14
• S2 citations—
• github stars0
• HF likes0
• heat score8.82
• arxiv keyluo2022tiny

Related papers

• Resource-efficient Separation Transformer (2022)7.81
• Attention Is All You Need In Speech Separation (2020)20.59
• Transmask: A Compact And Fast Speech Separation Model Based On Transformer (2021)8.82
• Exploring Self-attention Mechanisms For Speech Separation (2022)12.54
• Multi-dimensional And Multi-scale Modeling For Speech Separation Optimized By Discriminative Learning (2023)0.00
• Multi-scale Feature Fusion Transformer Network For End-to-end Single Channel Speech Separation (2022)0.00
• On Time Domain Conformer Models For Monaural Speech Separation In Noisy Reverberant Acoustic Environments (2023)5.84
• Tf-locoformer: Transformer With Local Modeling By Convolution For Speech Separation And Enhancement (2024)10.35