# TFCN: Temporal-Frequential Convolutional Network for Single-Channel Speech Enhancement

arXiv: https://arxiv.org/abs/2201.00480 · HTML: https://mlsanity.com/paper/2201.00480/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jan 2022.

## Built on by (most cited first, 1 of 1)

- [Scalable Speech Enhancement with Dynamic Channel Pruning](https://mlsanity.com/paper/2412.17121/) (2024)

## Abstract (arXiv)

Deep learning based single-channel speech enhancement tries to train a neural network model for the prediction of clean speech signal. There are a variety of popular network structures for single-channel speech enhancement, such as TCNN, UNet, WaveNet, etc. However, these structures usually contain millions of parameters, which is an obstacle for mobile applications. In this work, we proposed a light weight neural network for speech enhancement named TFCN. It is a temporal-frequential convolutional network constructed of dilated convolutions and depth-separable convolutions. We evaluate the performance of TFCN in terms of Short-Time Objective Intelligibility (STOI), perceptual evaluation of speech quality (PESQ) and a series of composite metrics named Csig, Cbak and Covl. Experimental results show that compared with TCN and several other state-of-the-art algorithms, the proposed structure achieves a comparable performance with only 93,000 parameters. Further improvement can be achieved at the cost of more parameters, by introducing dense connections and depth-separable convolutions with normal ones. Experiments also show that the proposed structure can work well both in causal and non-causal situations.