Pith. sign in

REVIEW 3 cited by

IR-GAN: Room Impulse Response Generator for Far-field Speech Recognition

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.13219 v3 pith:O6Q34425 submitted 2020-10-25 cs.SD eess.AS

classification cs.SDeess.AS
keywords rirssyntheticfar-fieldspeechimpulseir-ganrecognitionreal-world
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present a Generative Adversarial Network (GAN) based room impulse response generator (IR-GAN) for generating realistic synthetic room impulse responses (RIRs). IR-GAN extracts acoustic parameters from captured real-world RIRs and uses these parameters to generate new synthetic RIRs. We use these generated synthetic RIRs to improve far-field automatic speech recognition in new environments that are different from the ones used in training datasets. In particular, we augment the far-field speech training set by convolving our synthesized RIRs with a clean LibriSpeech dataset. We evaluate the quality of our synthetic RIRs on the real-world LibriSpeech test set created using real-world RIRs from the BUT ReverbDB and AIR datasets. Our IR-GAN reports up to an 8.95% lower error rate than Geometric Acoustic Simulator (GAS) in far-field speech recognition benchmarks. We further improve the performance when we combine our synthetic RIRs with synthetic impulse responses generated using GAS. This combination can reduce the word error rate by up to 14.3% in far-field speech recognition benchmarks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Explicit Context-Driven Neural Acoustic Modeling for High-Fidelity RIR Generation

    cs.SD 2025-09 conditional novelty 6.0 of 10

    Ray-casting local geometry features from a rough mesh into a neural acoustic field improves room impulse response prediction, especially with little training data.

  2. NAT: Neural Acoustic Transfer for Interactive Scenes in Real Time

    cs.SD 2025-06 conditional novelty 6.0 of 10

    NAT predicts acoustic transfer maps for dynamically changing scenes in 1-4 ms using a neural field trained on fast boundary element simulations.

  3. Room Impulse Response Generation Conditioned on Acoustic Parameters

    cs.SD 2025-07 conditional novelty 5.0 of 10

    MaskGIT conditioned on acoustic parameters, operating on Descript Audio Codec tokens, generates room impulse responses that outperform StoRIR and FastRIR in objective and MUSHRA evaluations.

Pith tools