Tensor-to-vector Regression For Multi-channel Speech Enhancement Based On Tensor-train Network

Abstract

We propose a tensor-to-vector regression approach to multi-channel speech enhancement in order to address the issue of input size explosion and hidden-layer size expansion. The key idea is to cast the conventional deep neural network (DNN) based vector-to-vector regression formulation under a tensor-train network (TTN) framework. TTN is a recently emerged solution for compact representation of deep models with fully connected hidden layers. Thus TTN maintains DNN's expressive power yet involves a much smaller amount of trainable parameters. Furthermore, TTN can handle a multi-dimensional tensor input by design, which exactly matches the desired setting in multi-channel speech enhancement. We first provide a theoretical extension from DNN to TTN based regression. Next, we show that TTN can attain speech enhancement quality comparable with that for DNN but with much fewer parameters, e.g., a reduction from 27 million to only 5 million parameters is observed in a single-channel scenario.

Stats

• citations15
• S2 citations—
• github stars47
• HF likes0
• heat score12.39
• arxiv keyqi2020tensor

Related papers

• Exploring Deep Hybrid Tensor-to-vector Network Architectures For Regression Based Speech Enhancement (2020)7.50
• Tensor-train Long Short-term Memory For Monaural Speech Enhancement (2018)0.00
• TFCN: Temporal-frequential Convolutional Network For Single-channel Speech Enhancement (2022)0.00
• Monaural Speech Enhancement Using A Multi-branch Temporal Convolutional Network (2019)3.58
• Exploiting Low-rank Tensor-train Deep Neural Networks Based On Riemannian Gradient Descent With Illustrations Of Speech Processing (2022)0.00
• TSTNN: Two-stage Transformer Based Neural Network For Speech Enhancement In The Time Domain (2021)16.73
• Consistency-aware Multi-channel Speech Enhancement Using Deep Neural Networks (2020)0.00
• Inter-channel Conv-tasnet For Multichannel Speech Enhancement (2021)0.00