Weighted Speech Distortion Losses For Neural-network-based Real-time Speech Enhancement

Abstract

This paper investigates several aspects of training a RNN (recurrent neural network) that impact the objective and subjective quality of enhanced speech for real-time single-channel speech enhancement. Specifically, we focus on a RNN that enhances short-time speech spectra on a single-frame-in, single-frame-out basis, a framework adopted by most classical signal processing methods. We propose two novel mean-squared-error-based learning objectives that enable separate control over the importance of speech distortion versus noise reduction. The proposed loss functions are evaluated by widely accepted objective quality and intelligibility measures and compared to other competitive online methods. In addition, we study the impact of feature normalization and varying batch sequence lengths on the objective quality of enhanced speech. Finally, we show subjective ratings for the proposed approach and a state-of-the-art real-time RNN-based method.

Stats

• citations85
• S2 citations—
• github stars0
• HF likes0
• heat score14.51
• arxiv keyxia2020weighted

Related papers

• A Consolidated View Of Loss Functions For Supervised Deep Learning-based Speech Enhancement (2020)13.93
• A Modulation-domain Loss For Neural-network-based Real-time Speech Enhancement (2021)8.09
• Effect Of Noise Suppression Losses On Speech Distortion And ASR Performance (2021)10.74
• Distortionless Multi-channel Target Speech Enhancement For Overlapped Speech Recognition (2020)0.00
• Speech And Noise Dual-stream Spectrogram Refine Network With Speech Distortion Loss For Robust Speech Recognition (2023)5.24
• Cheapnet: Improving Light-weight Speech Enhancement Network By Projected Loss Function (2023)0.00
• Consistency-aware Multi-channel Speech Enhancement Using Deep Neural Networks (2020)0.00
• Plugin Speech Enhancement: A Universal Speech Enhancement Framework Inspired By Dynamic Neural Network (2024)0.00