{"url":"/dataset/fluent-speech-commands","name":"Fluent Speech Commands","full_name":null,"description_markdown":"Fluent Speech Commands is an open source audio dataset for spoken language understanding (SLU) experiments. Each utterance is labeled with \"action\", \"object\", and \"location\" values; for example, \"turn the lights on in the kitchen\" has the label {\"action\": \"activate\", \"object\": \"lights\", \"location\": \"kitchen\"}. A model must predict each of these values, and a prediction for an utterance is deemed to be correct only if all values are correct. \r\n\r\nThe task is very simple, but the dataset is large and flexible to allow for many types of experiments: for instance, one can vary the number of speakers, or remove all instances of a particular sentence and test whether a model trained on the remaining sentences can generalize.","description_withheld":null,"homepage":"https://fluent.ai/fluent-speech-commands-a-dataset-for-spoken-language-understanding-research/","introduced_date":"2019-04-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/speech-model-pre-training-for-end-to-end","title":"Speech Model Pre-training for End-to-End Spoken Language Understanding","first_author":"Loren Lugosch","url":null},"license":{"name":"Custom (research-only)","url":"https://fluent.ai/fluent-speech-commands-a-dataset-for-spoken-language-understanding-research/"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Spoken Language Understanding","url":"/task/spoken-language-understanding","datasets_with_task":"/datasets/task/spoken-language-understanding"},{"name":"Voice Query Recognition","url":"/task/voice-query-recognition","datasets_with_task":"/datasets/task/voice-query-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Fluent Speech Commands"],"data_loaders":[{"repo":"https://github.com/rayyanahmed26042005/git-G160","url":"https://github.com/rayyanahmed26042005/git-G160","frameworks":["tf"]}],"num_papers_in_archive":57,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/spoken-language-understanding-on-fluent","task":"Spoken Language Understanding","dataset_variant":"Fluent Speech Commands","rows":17,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Finstreder (Conformer + AMT, character-based)","paper":"/paper/finstreder-simple-and-fast-spoken-language","metrics":{"Accuracy (%)":"99.8"},"code_links":[{"title":"Jaco-Assistant/Jaco-Master","url":"https://gitlab.com/Jaco-Assistant/Jaco-Master"},{"title":"Jaco-Assistant/finstreder","url":"https://gitlab.com/Jaco-Assistant/finstreder"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/universlu-universal-spoken-language","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","date":"2023-10-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/speechprompt-v2-prompt-tuning-for-speech","title":"SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks","date":"2023-03-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/finstreder-simple-and-fast-spoken-language","title":"Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models","date":"2022-06-29","rows_on_this_dataset":5,"code_links":2,"syntology":null},{"paper":"/paper/do-we-still-need-automatic-speech-recognition","title":"Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?","date":"2021-11-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/fans-fusing-asr-and-nlu-for-on-device-slu","title":"FANS: Fusing ASR and NLU for on-device SLU","date":"2021-10-31","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/end-to-end-spoken-language-understanding-for","title":"End-to-End Spoken Language Understanding for Generalized Voice Assistants","date":"2021-06-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sequential-end-to-end-intent-and-slot-label","title":"Sequential End-to-End Intent and Slot Label Classification and Localization","date":"2021-06-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/integration-of-pre-trained-networks-with","title":"Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding","date":"2021-04-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/speech-language-pre-training-for-end-to-end","title":"Speech-language Pre-training for End-to-end Spoken Language Understanding","date":"2021-02-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/exploring-transfer-learning-for-end-to-end","title":"Exploring Transfer Learning For End-to-End Spoken Language Understanding","date":"2020-12-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/two-stage-textual-knowledge-distillation-to","title":"Two-stage Textual Knowledge Distillation for End-to-End Spoken Language Understanding","date":"2020-10-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-end-to-end-speech-to-intent","title":"Improving End-to-End Speech-to-Intent Classification with Reptile","date":"2020-08-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/speech-model-pre-training-for-end-to-end","title":"Speech Model Pre-training for End-to-End Spoken Language Understanding","date":"2019-04-07","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}