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

• URL: http://arxiv.org/abs/2608.20971v1
• Date: Fri, 21 Aug 2026 10:50:00 GMT
• Title: Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement
• Abstract summary: We investigate how the realism of synthetic room impulse response (RIR) datasets affects the training of DeepFilterNet3 for single-channel speech enhancement.<n>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.<n>Training with the higher-fidelity dataset consistently yields modest improvements in objective metrics and substantially lower ASR word error rates.
• Score: 0.9617245548268437
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Improving multichannel speech enhancement through accurate room-acoustic simulations [0.9617245548268437]
  Training on the high-fidelity dataset results in an up to 38 % relative reduction in median word error rate compared to the lower-fidelity alternatives.<n>These results show that augmentation with high-fidelity room-acoustic simulations directly translates into improved multichannel speech enhancement performance.
  arXiv  Detail & Related papers  (2026-06-30T12:10:29Z)
• Data-Driven Deep MIMO Detection:Network Architectures and Generalization Analysis [50.20709408241935]
  This paper proposes inspecting the fully data-driven DeepSIC detection within a Network-of-MLPs architecture.<n>Within such an architecture, DeepSIC can be upgraded as a graph-based message-passing process using Graph Neural Networks (GNNs)<n>GNNSIC achieves excellent expressivity comparable to DeepSIC with substantially fewer trainable parameters.
  arXiv  Detail & Related papers  (2026-02-13T04:38:51Z)
• Studying the Role of Synthetic Data for Machine Learning-based Wireless Networks Traffic Forecasting [1.1699027359021665]
  This paper proposes a novel method to generate synthetic data, based on first-order auto-regressive noise statistics, for large-scale Wi-Fi deployments.<n> Experimental results show that ML models trained on synthetic data achieve Mean Absolute Error (MAE) values within 10 to 15 of those obtained using real data.<n>When generalization is required, synthetic-data-trained models improve prediction accuracy by up to 50 percent compared to real-data-trained baselines.
  arXiv  Detail & Related papers  (2026-01-12T15:27:55Z)
• Treble10: A high-quality dataset for far-field speech recognition, dereverberation, and enhancement [2.6008293644386904]
  We introduce Treble10, a large-scale, physically accurate room-acoustic dataset.<n> Treble10 contains over 3000 broadband room impulse responses (RIRs) simulated in 10 fully furnished real-world rooms.<n>All signals are simulated at 32 kHz, accurately modelling low-frequency wave effects and high-frequency reflections.
  arXiv  Detail & Related papers  (2025-10-27T09:17:44Z)
• Explicit Context-Driven Neural Acoustic Modeling for High-Fidelity RIR Generation [17.013738637228553]
  We present Mesh-infused Neural Acoustic Field (MiNAF), which queries a rough room mesh at given locations and extracts distance distributions as an explicit representation of local context.<n>Our approach demonstrates that incorporating explicit local geometric features can better guide the neural network in generating more accurate RIR predictions.
  arXiv  Detail & Related papers  (2025-09-18T17:57:07Z)
• Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark [65.79402756995084]
  Real Acoustic Fields (RAF) is a new dataset that captures real acoustic room data from multiple modalities. RAF is the first dataset to provide densely captured room acoustic data.
  arXiv  Detail & Related papers  (2024-03-27T17:59:56Z)
• AV-RIR: Audio-Visual Room Impulse Response Estimation [49.469389715876915]
  Accurate estimation of Room Impulse Response (RIR) is important for speech processing and AR/VR applications. We propose AV-RIR, a novel multi-modal multi-task learning approach to accurately estimate the RIR from a given reverberant speech signal and visual cues of its corresponding environment.
  arXiv  Detail & Related papers  (2023-11-30T22:58:30Z)
• Synthetic Wave-Geometric Impulse Responses for Improved Speech Dereverberation [69.1351513309953]
  We show that accurately simulating the low-frequency components of Room Impulse Responses (RIRs) is important to achieving good dereverberation. We demonstrate that speech dereverberation models trained on hybrid synthetic RIRs outperform models trained on RIRs generated by prior geometric ray tracing methods.
  arXiv  Detail & Related papers  (2022-12-10T20:15:23Z)
• Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding [76.89426311082927]
  Existing models are trained on clean data, which causes a textitgap between clean data training and real-world inference. We propose a method from the perspective of domain adaptation, by which both high- and low-quality samples are embedding into similar vector space. Experiments on the widely-used dataset, Snips, and large scale in-house dataset (10 million training examples) demonstrate that this method not only outperforms the baseline models on real-world (noisy) corpus but also enhances the robustness, that is, it produces high-quality results under a noisy environment.
  arXiv  Detail & Related papers  (2021-04-13T17:54:33Z)
• Conditioning Trick for Training Stable GANs [70.15099665710336]
  We propose a conditioning trick, called difference departure from normality, applied on the generator network in response to instability issues during GAN training. We force the generator to get closer to the departure from normality function of real samples computed in the spectral domain of Schur decomposition.
  arXiv  Detail & Related papers  (2020-10-12T16:50:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.