On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement

TL;DR

This paper investigates how different loss functions affect the performance of deep learning-based monaural time-domain speech enhancement, highlighting the advantages of perceptually inspired losses and SI-SDR for better speech quality.

Contribution

It provides a comprehensive analysis of loss functions in time-domain speech enhancement, emphasizing perceptual losses, the importance of learning rate, and the effectiveness of SI-SDR as a general-purpose loss.

Findings

Perceptually inspired loss functions may improve speech quality for human listeners.

The learning rate significantly impacts training effectiveness in speech enhancement models.

SI-SDR-based loss performs well across multiple evaluation metrics.

Abstract

Many deep learning-based speech enhancement algorithms are designed to minimize the mean-square error (MSE) in some transform domain between a predicted and a target speech signal. However, optimizing for MSE does not necessarily guarantee high speech quality or intelligibility, which is the ultimate goal of many speech enhancement algorithms. Additionally, only little is known about the impact of the loss function on the emerging class of time-domain deep learning-based speech enhancement systems. We study how popular loss functions influence the performance of deep learning-based speech enhancement systems. First, we demonstrate that perceptually inspired loss functions might be advantageous if the receiver is the human auditory system. Furthermore, we show that the learning rate is a crucial design parameter even for adaptive gradient-based optimizers, which has been generally overlooked in the literature. Also, we found that waveform matching performance metrics must be used with caution as they in certain situations can fail completely. Finally, we show that a loss function based on scale-invariant signal-to-distortion ratio (SI-SDR) achieves good general performance across a range of popular speech enhancement evaluation metrics, which suggests that SI-SDR is a good candidate as a general-purpose loss function for speech enhancement systems.