{"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/speech-commands-a-dataset-for-limited","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","arxiv_id":"1804.03209","date":"2018-04-09","proceeding":null,"authors":["Pete Warden"],"abstract":"Describes an audio dataset of spoken words designed to help train and\nevaluate keyword spotting systems. Discusses why this task is an interesting\nchallenge, and why it requires a specialized dataset that is different from\nconventional datasets used for automatic speech recognition of full sentences.\nSuggests a methodology for reproducible and comparable accuracy metrics for\nthis task. Describes how the data was collected and verified, what it contains,\nprevious versions and properties. Concludes by reporting baseline results of\nmodels trained on this dataset.","url_abs":"http://arxiv.org/abs/1804.03209v1","url_pdf":"http://arxiv.org/pdf/1804.03209v1.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":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/Abdallah-Hesham99/tell_your_motor_speed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/Alpe6825/Unicornn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/Benja1972/Speech_recognition_Tensorflow2.0","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/Cbhihe/classify_sound_mobile","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/Qualcomm-AI-research/bcresnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/ROBOTICSENGINEER/End_to_End_Learning_of_Speech_2D_Feature_Trajectory","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/Snapchat/snapml-templates","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/TMarquet/speech_recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/TomVeniat/SANAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/akommini/Spoken-Numeric-Digit-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/ayyucedemirbas/gcommands_12_classes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/bozliu/E2E-Keyword-Spotting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/dapeter/nas-for-kws","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/diggerdu/AudioMamba","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/diggerdu/audiorwkv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/fracorti/reds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/idiap/sparch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/jarfo/gcommands","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/lukesin/nas-for-kws-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/maxtimer97/ssm-inspired-lif","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/ncsoft/phonmatchnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/phanxuanphucnd/wav2kws","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/pspratling/Speech-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/pulp-platform/eae-kws","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/qute012/Wav2Keyword","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/retrocirce/hts-audio-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/rf5/simple-speech-commands","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/sankalp2610/Speech_Command_Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/saraalemadi/DroneAudioDataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/tae-jun/sampleaudio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/toopster/dsc-capstone-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/unibe-cns/gle-code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/widzemin/audio_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"speech-commands-a-dataset-for-limited","repo_url":"https://github.com/zhenghuatan/audio-adversarial-examples","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"keyword-spotting","task_name":"Keyword Spotting"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"}],"methods":[],"datasets_introduced":[{"slug":"speech-commands","name":"Speech Commands","full_name":"Speech Commands"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/keyword-spotting-on-tensorflow","task":"Keyword Spotting","dataset":"TensorFlow","model":"TensorFlow's model version 2","rank_in_archive_order":1,"of":2,"metrics":{"TFMA":"89.7"},"uses_additional_data":false},{"leaderboard":"/sota/keyword-spotting-on-tensorflow","task":"Keyword Spotting","dataset":"TensorFlow","model":"TensorFlow's model version 1","rank_in_archive_order":2,"of":2,"metrics":{"TFMA":"85.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.03209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.03209"}},"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/retrocirce/hts-audio-transformer","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sankalp2610/Speech_Command_Recognition","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Cbhihe/classify_sound_mobile","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Alpe6825/Unicornn","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/diggerdu/AudioMamba","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qualcomm-AI-research/bcresnet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ncsoft/phonmatchnet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ROBOTICSENGINEER/End_to_End_Learning_of_Speech_2D_Feature_Trajectory","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rf5/simple-speech-commands","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ayyucedemirbas/gcommands_12_classes","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/diggerdu/audiorwkv","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/idiap/sparch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TMarquet/speech_recognition","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/unibe-cns/gle-code","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fracorti/reds","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pspratling/Speech-Recognition","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/widzemin/audio_project","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pulp-platform/eae-kws","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/toopster/dsc-capstone-project","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Abdallah-Hesham99/tell_your_motor_speed","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maxtimer97/ssm-inspired-lif","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dapeter/nas-for-kws","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TomVeniat/SANAS","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phanxuanphucnd/wav2kws","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":4,"unverified":1},"by_repo_kind":{"listed":{"samples":5,"ran":4,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"9cac4e2f77d0fdbb","entry":"fix","repo":"rf5/simple-speech-commands","repo_kind":"listed","path":"convrnn_classifier.py","file_url":"https://github.com/rf5/simple-speech-commands/blob/HEAD/convrnn_classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9cac4e2f77d0fdbb"}},{"code_sha256_prefix":"1ca2cf37c52647b2","entry":"get_segment","repo":"jarfo/gcommands","repo_kind":"listed","path":"gcommands_loader.py","file_url":"https://github.com/jarfo/gcommands/blob/HEAD/gcommands_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1ca2cf37c52647b2"}},{"code_sha256_prefix":"2464f4579c713218","entry":"make_dataset","repo":"jarfo/gcommands","repo_kind":"listed","path":"gcommands_loader.py","file_url":"https://github.com/jarfo/gcommands/blob/HEAD/gcommands_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2464f4579c713218"}},{"code_sha256_prefix":"d5d9fe74e6860724","entry":"make_layers","repo":"jarfo/gcommands","repo_kind":"listed","path":"model.py","file_url":"https://github.com/jarfo/gcommands/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d5d9fe74e6860724"}},{"code_sha256_prefix":"18848a23153cea46","entry":"wav_read","repo":"jarfo/gcommands","repo_kind":"listed","path":"gcommands_loader.py","file_url":"https://github.com/jarfo/gcommands/blob/HEAD/gcommands_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"18848a23153cea46"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}