{"url":"/sota/spoken-language-understanding-on-fluent","task":{"name":"Spoken Language Understanding","url":"/task/spoken-language-understanding","note":null},"dataset":{"name":"Fluent Speech Commands","url":"/dataset/fluent-speech-commands"},"category":"Speech","categories":["Speech"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy (%)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy (%)":"higher"}},"counts":{"rows":17,"rows_with_code":7,"rows_with_paper_page":17,"rows_dated":17,"rows_using_additional_data":17},"rows":[{"rank_in_archive_order":1,"model":"Finstreder (Conformer + AMT, character-based)","metrics":{"Accuracy (%)":"99.8"},"uses_additional_data":true,"paper_date":"2022-06-29","paper":"/paper/finstreder-simple-and-fast-spoken-language","paper_url":"https://arxiv.org/abs/2206.14589v1","paper_title":"Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models","code":"https://gitlab.com/Jaco-Assistant/Jaco-Master","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"UniverSLU","metrics":{"Accuracy (%)":"99.8"},"uses_additional_data":true,"paper_date":"2023-10-04","paper":"/paper/universlu-universal-spoken-language","paper_url":"https://arxiv.org/abs/2310.02973v2","paper_title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Finstreder (Quartznet + AMT)","metrics":{"Accuracy (%)":"99.7"},"uses_additional_data":true,"paper_date":"2022-06-29","paper":"/paper/finstreder-simple-and-fast-spoken-language","paper_url":"https://arxiv.org/abs/2206.14589v1","paper_title":"Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models","code":"https://gitlab.com/Jaco-Assistant/Jaco-Master","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"textual-kd-slu","metrics":{"Accuracy (%)":"99.7"},"uses_additional_data":true,"paper_date":"2020-10-25","paper":"/paper/two-stage-textual-knowledge-distillation-to","paper_url":"https://arxiv.org/abs/2010.13105v2","paper_title":"Two-stage Textual Knowledge Distillation for End-to-End Spoken Language Understanding","code":"https://github.com/clovaai/textual-kd-slu","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Wav2Vec2.0-Classifier","metrics":{"Accuracy (%)":"99.7"},"uses_additional_data":true,"paper_date":"2021-04-15","paper":"/paper/integration-of-pre-trained-networks-with","paper_url":"https://arxiv.org/abs/2104.07253v2","paper_title":"Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"E2E SLP two-step","metrics":{"Accuracy (%)":"99.7"},"uses_additional_data":true,"paper_date":"2021-02-11","paper":"/paper/speech-language-pre-training-for-end-to-end","paper_url":"https://arxiv.org/abs/2102.06283v1","paper_title":"Speech-language Pre-training for End-to-end Spoken Language Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"Wav2vec 2.0 SSL","metrics":{"Accuracy (%)":"99.6"},"uses_additional_data":true,"paper_date":"2021-11-29","paper":"/paper/do-we-still-need-automatic-speech-recognition","paper_url":"https://arxiv.org/abs/2111.14842v1","paper_title":"Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"Finstreder (Conformer)","metrics":{"Accuracy (%)":"99.5"},"uses_additional_data":true,"paper_date":"2022-06-29","paper":"/paper/finstreder-simple-and-fast-spoken-language","paper_url":"https://arxiv.org/abs/2206.14589v1","paper_title":"Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models","code":"https://gitlab.com/Jaco-Assistant/Jaco-Master","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"AT-AT","metrics":{"Accuracy (%)":"99.5"},"uses_additional_data":true,"paper_date":"2020-12-15","paper":"/paper/exploring-transfer-learning-for-end-to-end","paper_url":"https://arxiv.org/abs/2012.08549v1","paper_title":"Exploring Transfer Learning For End-to-End Spoken Language Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"BERT, AC Pretraining","metrics":{"Accuracy (%)":"99.4"},"uses_additional_data":true,"paper_date":"2021-06-16","paper":"/paper/end-to-end-spoken-language-understanding-for","paper_url":"https://arxiv.org/abs/2106.09009v2","paper_title":"End-to-End Spoken Language Understanding for Generalized Voice Assistants","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"3D-CNN+LSTM+CE","metrics":{"Accuracy (%)":"99.3"},"uses_additional_data":true,"paper_date":"2021-06-08","paper":"/paper/sequential-end-to-end-intent-and-slot-label","paper_url":"https://arxiv.org/abs/2106.04660v1","paper_title":"Sequential End-to-End Intent and Slot Label Classification and Localization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"Finstreder (Quartznet)","metrics":{"Accuracy (%)":"99.2"},"uses_additional_data":true,"paper_date":"2022-06-29","paper":"/paper/finstreder-simple-and-fast-spoken-language","paper_url":"https://arxiv.org/abs/2206.14589v1","paper_title":"Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models","code":"https://gitlab.com/Jaco-Assistant/Jaco-Master","n_code_links":2,"syntology":null},{"rank_in_archive_order":13,"model":"Reptile","metrics":{"Accuracy (%)":"99.2"},"uses_additional_data":true,"paper_date":"2020-08-05","paper":"/paper/improving-end-to-end-speech-to-intent","paper_url":"https://arxiv.org/abs/2008.01994v1","paper_title":"Improving End-to-End Speech-to-Intent Classification with Reptile","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"FANS","metrics":{"Accuracy (%)":"99.0"},"uses_additional_data":true,"paper_date":"2021-10-31","paper":"/paper/fans-fusing-asr-and-nlu-for-on-device-slu","paper_url":"https://arxiv.org/abs/2111.00400v1","paper_title":"FANS: Fusing ASR and NLU for on-device SLU","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"Pooling classifier pre-trained using force-aligned phoneme and word labels on LibriSpeech","metrics":{"Accuracy (%)":"98.8"},"uses_additional_data":true,"paper_date":"2019-04-07","paper":"/paper/speech-model-pre-training-for-end-to-end","paper_url":"https://arxiv.org/abs/1904.03670v2","paper_title":"Speech Model Pre-training for End-to-End Spoken Language Understanding","code":"https://github.com/dscripka/openwakeword","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"Amazon Alexa","metrics":{"Accuracy (%)":"98.7"},"uses_additional_data":true,"paper_date":"2022-06-29","paper":"/paper/finstreder-simple-and-fast-spoken-language","paper_url":"https://arxiv.org/abs/2206.14589v1","paper_title":"Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models","code":"https://gitlab.com/Jaco-Assistant/Jaco-Master","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"pGSLM+","metrics":{"Accuracy (%)":"98.2"},"uses_additional_data":true,"paper_date":"2023-03-01","paper":"/paper/speechprompt-v2-prompt-tuning-for-speech","paper_url":"https://arxiv.org/abs/2303.00733v1","paper_title":"SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}