mlsanityData to 7 Oct 2026

FAST-RIR: Fast neural diffuse room impulse response generator

arXiv 2110.04057 ↗First posted 7 Oct 2021cs.SD cs.AI cs.LGcited by 35

Not on the map. Why?

Abstract (arXiv)

We present a neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment. Our FAST-RIR takes rectangular room dimensions, listener and speaker positions, and reverberation time as inputs and generates specular and diffuse reflections for a given acoustic environment. Our FAST-RIR is capable of generating RIRs for a given input reverberation time with an average error of 0.02s. We evaluate our generated RIRs in automatic speech recognition (ASR) applications using Google Speech API, Microsoft Speech API, and Kaldi tools. We show that our proposed FAST-RIR with batch size 1 is 400 times faster than a state-of-the-art diffuse acoustic simulator (DAS) on a CPU and gives similar performance to DAS in ASR experiments. Our FAST-RIR is 12 times faster than an existing GPU-based RIR generator (gpuRIR). We show that our FAST-RIR outperforms gpuRIR by 2.5% in an AMI far-field ASR benchmark.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 13 of its 36 references that are in the map. First posted on arXiv 7 Oct 2021.

Builds on

13 of 36 references.

References · 13

  1. 2014Conditional Generative Adversarial Netscited by 2,152
  2. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  3. 2019GANSynth: Adversarial Neural Audio Synthesiscited by 114
  4. 2018gpuRIR: A Python Library for Room Impulse Response Simulation with GPU Accelerationcited by 46
  5. 2018Building and Evaluation of a Real Room Impulse Response Datasetcited by 43
  6. 2021Image2Reverb: Cross-Modal Reverb Impulse Response Synthesiscited by 34
  7. 2021TS-RIR: Translated synthetic room impulse responses for speech augmentationcited by 12
  8. 2019Improving Reverberant Speech Training Using Diffuse Acoustic Simulationcited by 9
  9. 2020Directional ASR: A New Paradigm for E2E Multi-Speaker Speech Recognition with Source Localizationcited by 8
  10. 2020Sound Synthesis, Propagation, and Rendering: A Surveycited by 6
  11. 2021Complex Neural Spatial Filter: Enhancing Multi-channel Target Speech Separation in Complex Domaincited by 3
  12. 2020StoRIR: Stochastic Room Impulse Response Generation for Audio Data Augmentationcited by 2
1 more
  1. 2021Scene-aware Far-field Automatic Speech Recognitioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 9; 2024: 9; 2025: 5; 2026: 7.

35 papers.

Sort:

By area:

  1. 2022Learning Neural Acoustic Fieldscited by 65
  2. 2023AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesiscited by 49
  3. 2022Few-Shot Audio-Visual Learning of Environment Acousticscited by 48
  4. 2022MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenescited by 23
  5. 2023Neural Acoustic Context Field: Rendering Realistic Room Impulse Response With Neural Fieldscited by 23
  6. 2023Measuring Acoustics with Collaborative Multiple Agentscited by 21
  7. 2023AV-RIR: Audio-Visual Room Impulse Response Estimationcited by 20
  8. 2024Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmarkcited by 20
  9. 2023AdVerb: Visually Guided Audio Dereverberationcited by 15
  10. 2024AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesiscited by 14
  11. 2023Listen2Scene: Interactive material-aware binaural sound propagation for reconstructed 3D scenescited by 10
  12. 2022Towards Improved Room Impulse Response Estimation for Speech Recognitioncited by 9
23 more
  1. 2024NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fieldscited by 8
  2. 2025Hearing Anywhere in Any Environmentcited by 8
  3. 2023Novel-View Acoustic Synthesis from 3D Reconstructed Roomscited by 6
  4. 2025Differentiable Room Acoustic Rendering with Multi-View Vision Priorscited by 5
  5. 2025How Would It Sound? Material-Controlled Multimodal Acoustic Profile Generation for Indoor Scenescited by 4
  6. 2024SOAF: Scene Occlusion-aware Neural Acoustic Fieldcited by 3
  7. 2024LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarizationcited by 3
  8. 2025SoundVista: Novel-View Ambient Sound Synthesis via Visual-Acoustic Bindingcited by 3
  9. 2024ActiveRIR: Active Audio-Visual Exploration for Acoustic Environment Modelingcited by 2
  10. 2026Few-shot Acoustic Synthesis with Multimodal Flow Matchingcited by 2
  11. 2023Bayesian inference and neural estimation of acoustic wave propagationcited by 1
  12. 2023An Integrated Algorithm for Robust and Imperceptible Audio Adversarial Examplescited by 1
  13. 2024Blind Spatial Impulse Response Generation from Separate Room- and Scene-Specific Informationcited by 1
  14. 2026Ambisonics Encoding of Room Impulse Responses using a Device-Agnostic Diffusion Modelcited by 1
  15. 2022MetaSpeech: Speech Effects Switch Along with Environment for Metaversecited by 0
  16. 2024MAGIC: Map-Guided Few-Shot Audio-Visual Acoustics Modelingcited by 0
  17. 2024SPEAR: Receiver-to-Receiver Acoustic Neural Warping Fieldcited by 0
  18. 2025PromptReverb: Multimodal Room Impulse Response Generation Through Latent Rectified Flow Matchingcited by 0
  19. 2026Room Impulse Response Completion Using Signal-Prediction Diffusion Models Conditioned on Simulated Early Reflectionscited by 0
  20. 2026Materialistic RIR: Material Conditioned Realistic RIR Generationcited by 0
  21. 2026Towards Improving Speaker Distance Estimation through Generative Impulse Response Augmentationcited by 0
  22. 2026SF-Flow: Sound field magnitude estimation via flow matching guided by sparse measurementscited by 0
  23. 2026PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulationcited by 0