# Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks

arXiv: https://arxiv.org/abs/2005.11611 · HTML: https://mlsanity.com/paper/2005.11611/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2020.

## Built on by (most cited first, 10 of 10)

- [Interspeech 2021 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2101.01902/) (2021)
- [Transformers with Competitive Ensembles of Independent Mechanisms](https://mlsanity.com/paper/2103.00336/) (2021)
- [Real-time Denoising and Dereverberation with Tiny Recurrent U-Net](https://mlsanity.com/paper/2102.03207/) (2021)
- [Investigating the Design Space of Diffusion Models for Speech Enhancement](https://mlsanity.com/paper/2312.04370/) (2023)
- [Training Speech Enhancement Systems with Noisy Speech Datasets](https://mlsanity.com/paper/2105.12315/) (2021)
- [Perceptual Contrast Stretching on Target Feature for Speech Enhancement](https://mlsanity.com/paper/2203.17152/) (2022)
- [Assessing the Generalization Gap of Learning-Based Speech Enhancement Systems in Noisy and Reverberant Environments](https://mlsanity.com/paper/2309.06183/) (2023)
- [Phase-Aware Deep Speech Enhancement: It's All About The Frame Length](https://mlsanity.com/paper/2203.16222/) (2022)
- [On Batching Variable Size Inputs for Training End-to-End Speech Enhancement Systems](https://mlsanity.com/paper/2301.10587/) (2023)
- [Speech Enhancement using Separable Polling Attention and Global Layer Normalization followed with PReLU](https://mlsanity.com/paper/2105.02509/) (2021)

## Abstract (arXiv)

Recently, deep neural networks (DNNs) have been successfully used for speech enhancement, and DNN-based speech enhancement is becoming an attractive research area. While time-frequency masking based on the short-time Fourier transform (STFT) has been widely used for DNN-based speech enhancement over the last years, time domain methods such as the time-domain audio separation network (TasNet) have also been proposed. The most suitable method depends on the scale of the dataset and the type of task. In this paper, we explore the best speech enhancement algorithm on two different datasets. We propose a STFT-based method and a loss function using problem-agnostic speech encoder (PASE) features to improve subjective quality for the smaller dataset. Our proposed methods are effective on the Voice Bank + DEMAND dataset and compare favorably to other state-of-the-art methods. We also implement a low-latency version of TasNet, which we submitted to the DNS Challenge and made public by open-sourcing it. Our model achieves excellent performance on the DNS Challenge dataset.