Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement

2026-08-21

AI Summary

研究通过使用高保真度的声学模拟数据训练DeepFilterNet3，以提高单通道语音增强效果，相比低精度数据，新方法显著降低了自动语音识别的词错误率。

Abstract

We investigate how the realism of synthetic room impulse response (RIR) datasets affects the training of DeepFilterNet3 for single-channel speech enhancement. We compare a DNS4 image-source-method (ISM) RIR dataset with a higher-acoustic-fidelity dataset generated using hybrid wave-based and geometrical acoustics simulation. Rather than isolating individual simulation factors, we compare complete RIR generation pipelines while keeping the enhancement model unchanged. Models are evaluated on unseen measured RIRs using objective speech enhancement metrics and downstream automatic speech recognition (ASR). Training with the higher-fidelity dataset consistently yields modest improvements in objective metrics and substantially lower ASR word error rates than the ISM dataset. Although the experiments do not attribute these gains to individual modelling components, they show that increasing the overall realism of synthetic acoustic training data improves the generalization of DeepFilterNet3 to unseen measured environments.

Problem

• synthetic room impulse response
• single-channel speech enhancement
• acoustic simulation

Innovation

• higher-acoustic-fidelity
• hybrid wave-based and geometrical acoustics simulation
• unseen measured RIRs