{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ir-gan-room-impulse-response-generator-for","title":"IR-GAN: Room Impulse Response Generator for Far-field Speech Recognition","arxiv_id":"2010.13219","date":"2020-10-25","proceeding":null,"authors":["Anton Ratnarajah","Zhenyu Tang","Dinesh Manocha"],"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.","url_abs":"https://arxiv.org/abs/2010.13219v3","url_pdf":"https://arxiv.org/pdf/2010.13219v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"ir-gan-room-impulse-response-generator-for","repo_url":"https://github.com/GAMMA-UMD/IR-GAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2010.13219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.13219"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/GAMMA-UMD/IR-GAN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"44c130f23fbe6729","entry":"WaveGANGenerator","repo":"GAMMA-UMD/IR-GAN","repo_kind":"official","path":"wavegan.py","file_url":"https://github.com/GAMMA-UMD/IR-GAN/blob/HEAD/wavegan.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"44c130f23fbe6729"}},{"code_sha256_prefix":"9d6ce1815be54da0","entry":"conv1d_transpose","repo":"GAMMA-UMD/IR-GAN","repo_kind":"official","path":"wavegan.py","file_url":"https://github.com/GAMMA-UMD/IR-GAN/blob/HEAD/wavegan.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d6ce1815be54da0"}},{"code_sha256_prefix":"ec163cf6a2ce4ac3","entry":"decode_audio","repo":"GAMMA-UMD/IR-GAN","repo_kind":"official","path":"loader.py","file_url":"https://github.com/GAMMA-UMD/IR-GAN/blob/HEAD/loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec163cf6a2ce4ac3"}},{"code_sha256_prefix":"2e53f90870fc8ffe","entry":"decode_extract_and_batch","repo":"GAMMA-UMD/IR-GAN","repo_kind":"official","path":"loader.py","file_url":"https://github.com/GAMMA-UMD/IR-GAN/blob/HEAD/loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e53f90870fc8ffe"}},{"code_sha256_prefix":"4e3a964a499dd04a","entry":"inception_score","repo":"GAMMA-UMD/IR-GAN","repo_kind":"official","path":"eval/inception/score.py","file_url":"https://github.com/GAMMA-UMD/IR-GAN/blob/HEAD/eval/inception/score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e3a964a499dd04a"}},{"code_sha256_prefix":"6f9251347b36fbe6","entry":"lrelu","repo":"GAMMA-UMD/IR-GAN","repo_kind":"official","path":"wavegan.py","file_url":"https://github.com/GAMMA-UMD/IR-GAN/blob/HEAD/wavegan.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f9251347b36fbe6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}