{"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/trainable-frontend-for-robust-and-far-field","title":"Trainable Frontend For Robust and Far-Field Keyword Spotting","arxiv_id":"1607.05666","date":"2016-07-19","proceeding":null,"authors":["Yuxuan Wang","Pascal Getreuer","Thad Hughes","Richard F. Lyon","Rif A. Saurous"],"abstract":"Robust and far-field speech recognition is critical to enable true hands-free\ncommunication. In far-field conditions, signals are attenuated due to distance.\nTo improve robustness to loudness variation, we introduce a novel frontend\ncalled per-channel energy normalization (PCEN). The key ingredient of PCEN is\nthe use of an automatic gain control based dynamic compression to replace the\nwidely used static (such as log or root) compression. We evaluate PCEN on the\nkeyword spotting task. On our large rerecorded noisy and far-field eval sets,\nwe show that PCEN significantly improves recognition performance. Furthermore,\nwe model PCEN as neural network layers and optimize high-dimensional PCEN\nparameters jointly with the keyword spotting acoustic model. The trained PCEN\nfrontend demonstrates significant further improvements without increasing model\ncomplexity or inference-time cost.","url_abs":"http://arxiv.org/abs/1607.05666v1","url_pdf":"http://arxiv.org/pdf/1607.05666v1.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":"abstracts"},"code_links":[{"paper_slug":"trainable-frontend-for-robust-and-far-field","repo_url":"https://github.com/simongrest/kaggle-freesound-audio-tagging-2019","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"trainable-frontend-for-robust-and-far-field","repo_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/master/asteroid_filterbanks/pcen.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"keyword-spotting","task_name":"Keyword Spotting"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1607.05666","atlas_url":"https://app.syntology.ai/?focus=1607.05666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.05666"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/simongrest/kaggle-freesound-audio-tagging-2019","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/master/asteroid_filterbanks/pcen.py","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"listed":{"samples":10,"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":"e27f2fb58bd944e4","entry":"batch_packed_1d_conv","repo":"asteroid-team/asteroid-filterbanks","repo_kind":"listed","path":"asteroid_filterbanks/enc_dec.py","file_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/HEAD/asteroid_filterbanks/enc_dec.py","link_basis":"harvester_set","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":"e27f2fb58bd944e4"}},{"code_sha256_prefix":"39ebbabf630b2f81","entry":"erb_scale_2_freq_hz","repo":"asteroid-team/asteroid-filterbanks","repo_kind":"listed","path":"asteroid_filterbanks/multiphase_gammatone_fb.py","file_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/HEAD/asteroid_filterbanks/multiphase_gammatone_fb.py","link_basis":"harvester_set","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":"39ebbabf630b2f81"}},{"code_sha256_prefix":"7ee826bfe8bb4bd1","entry":"gammatone_impulse_response","repo":"asteroid-team/asteroid-filterbanks","repo_kind":"listed","path":"asteroid_filterbanks/multiphase_gammatone_fb.py","file_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/HEAD/asteroid_filterbanks/multiphase_gammatone_fb.py","link_basis":"harvester_set","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":"7ee826bfe8bb4bd1"}},{"code_sha256_prefix":"779d3152b94b1fb5","entry":"generate_mpgtf","repo":"asteroid-team/asteroid-filterbanks","repo_kind":"listed","path":"asteroid_filterbanks/multiphase_gammatone_fb.py","file_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/HEAD/asteroid_filterbanks/multiphase_gammatone_fb.py","link_basis":"harvester_set","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":"779d3152b94b1fb5"}},{"code_sha256_prefix":"8923f688906e1436","entry":"griffin_lim","repo":"asteroid-team/asteroid-filterbanks","repo_kind":"listed","path":"asteroid_filterbanks/griffin_lim.py","file_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/HEAD/asteroid_filterbanks/griffin_lim.py","link_basis":"harvester_set","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":"8923f688906e1436"}},{"code_sha256_prefix":"8de8d30f605a4889","entry":"mark_deprecated","repo":"asteroid-team/asteroid-filterbanks","repo_kind":"listed","path":"asteroid_filterbanks/deprecation.py","file_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/HEAD/asteroid_filterbanks/deprecation.py","link_basis":"harvester_set","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":"8de8d30f605a4889"}},{"code_sha256_prefix":"93bfd5f9c97e18fb","entry":"misi","repo":"asteroid-team/asteroid-filterbanks","repo_kind":"listed","path":"asteroid_filterbanks/griffin_lim.py","file_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/HEAD/asteroid_filterbanks/griffin_lim.py","link_basis":"harvester_set","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":"93bfd5f9c97e18fb"}},{"code_sha256_prefix":"5d963eb6c86771b1","entry":"perfect_synthesis_window","repo":"asteroid-team/asteroid-filterbanks","repo_kind":"listed","path":"asteroid_filterbanks/stft_fb.py","file_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/HEAD/asteroid_filterbanks/stft_fb.py","link_basis":"harvester_set","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":"5d963eb6c86771b1"}},{"code_sha256_prefix":"a84548a7c681b48d","entry":"script_if_tracing","repo":"asteroid-team/asteroid-filterbanks","repo_kind":"listed","path":"asteroid_filterbanks/scripting.py","file_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/HEAD/asteroid_filterbanks/scripting.py","link_basis":"harvester_set","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":"a84548a7c681b48d"}},{"code_sha256_prefix":"a518652d7056ad7f","entry":"square_ola","repo":"asteroid-team/asteroid-filterbanks","repo_kind":"listed","path":"asteroid_filterbanks/torch_stft_fb.py","file_url":"https://github.com/asteroid-team/asteroid-filterbanks/blob/HEAD/asteroid_filterbanks/torch_stft_fb.py","link_basis":"harvester_set","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":"a518652d7056ad7f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}