{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/speechocean762","name":"speechocean762","full_name":null,"description_markdown":"speechocean762 is an open-source speech corpus designed for pronunciation assessment use, consisting of 5000 English utterances from 250 non-native speakers, where half of the speakers are children. Five experts annotated each of the utterances at sentence-level, word-level and phoneme-level. This corpus is allowed to be used freely for commercial and non-commercial purposes. To avoid subjective bias, each expert scores independently under the same metric","description_withheld":null,"homepage":"https://www.openslr.org/101","introduced_date":"2021-04-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/speechocean762-an-open-source-non-native","title":"speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment","first_author":"Junbo Zhang","url":null},"license":{"name":"Attribution 4.0 International (CC BY 4.0)","url":"https://www.apache.org/licenses/LICENSE-2.0"},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Phone-level pronunciation scoring","url":"/task/phone-level-pronunciation-scoring","datasets_with_task":"/datasets/task/phone-level-pronunciation-scoring"},{"name":"Word-level pronunciation scoring","url":"/task/word-level-pronunciation-scoring","datasets_with_task":"/datasets/task/word-level-pronunciation-scoring"},{"name":"Utterance-level pronounciation scoring","url":"/task/utterance-level-pronounciation-scoring","datasets_with_task":"/datasets/task/utterance-level-pronounciation-scoring"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["speechocean762"],"data_loaders":[],"num_papers_in_archive":14,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/phone-level-pronunciation-scoring-on","task":"Phone-level pronunciation scoring","dataset_variant":"speechocean762","rows":8,"metrics":["Pearson correlation coefficient (PCC)"],"first_row_in_archive_order":{"model":"HierCB+ConPCO","paper":"/paper/conpco-preserving-phoneme-characteristics-for","metrics":{"Pearson correlation coefficient (PCC)":"0.701"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/utterance-level-pronounciation-scoring-on","task":"Utterance-level pronounciation scoring","dataset_variant":"speechocean762","rows":5,"metrics":["Pearson correlation coefficient (PCC)"],"first_row_in_archive_order":{"model":"3MH","paper":"/paper/a-hierarchical-context-aware-modeling","metrics":{"Pearson correlation coefficient (PCC)":"0.811"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/word-level-pronunciation-scoring-on","task":"Word-level pronunciation scoring","dataset_variant":"speechocean762","rows":5,"metrics":["Pearson correlation coefficient (PCC)"],"first_row_in_archive_order":{"model":"3MH","paper":"/paper/a-hierarchical-context-aware-modeling","metrics":{"Pearson correlation coefficient (PCC)":"0.694"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":7,"of":7,"counts":{"papers_with_a_benchmark_row":7,"with_a_code_link":4,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":7,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/conpco-preserving-phoneme-characteristics-for","slug":"conpco-preserving-phoneme-characteristics-for","title":"ConPCO: Preserving Phoneme Characteristics for Automatic Pronunciation Assessment Leveraging Contrastive Ordinal Regularization","date":"2024-06-05","arxiv_id":"2406.02859","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-self-supervised-learning-models","slug":"fine-tuning-self-supervised-learning-models","title":"Fine-Tuning Self-Supervised Learning Models for End-to-End Pronunciation Scoring","date":"2023-09-19","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-hierarchical-context-aware-modeling","slug":"a-hierarchical-context-aware-modeling","title":"A Hierarchical Context-aware Modeling Approach for Multi-aspect and Multi-granular Pronunciation Assessment","date":"2023-05-29","arxiv_id":"2305.18146","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/hierarchical-pronunciation-assessment-with","slug":"hierarchical-pronunciation-assessment-with","title":"Hierarchical Pronunciation Assessment with Multi-Aspect Attention","date":"2022-11-15","arxiv_id":"2211.08102","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/speechblender-speech-augmentation-framework","slug":"speechblender-speech-augmentation-framework","title":"SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generation","date":"2022-11-02","arxiv_id":"2211.00923","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/transformer-based-multi-aspect-multi","slug":"transformer-based-multi-aspect-multi","title":"Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment","date":"2022-05-06","arxiv_id":"2205.03432","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/speechocean762-an-open-source-non-native","slug":"speechocean762-an-open-source-non-native","title":"speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment","date":"2021-04-03","arxiv_id":"2104.01378","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/conpco-preserving-phoneme-characteristics-for","slug":"conpco-preserving-phoneme-characteristics-for","title":"ConPCO: Preserving Phoneme Characteristics for Automatic Pronunciation Assessment Leveraging Contrastive Ordinal Regularization","date":"2024-06-05","arxiv_id":"2406.02859","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-self-supervised-learning-models","slug":"fine-tuning-self-supervised-learning-models","title":"Fine-Tuning Self-Supervised Learning Models for End-to-End Pronunciation Scoring","date":"2023-09-19","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-hierarchical-context-aware-modeling","slug":"a-hierarchical-context-aware-modeling","title":"A Hierarchical Context-aware Modeling Approach for Multi-aspect and Multi-granular Pronunciation Assessment","date":"2023-05-29","arxiv_id":"2305.18146","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/hierarchical-pronunciation-assessment-with","slug":"hierarchical-pronunciation-assessment-with","title":"Hierarchical Pronunciation Assessment with Multi-Aspect Attention","date":"2022-11-15","arxiv_id":"2211.08102","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/speechblender-speech-augmentation-framework","slug":"speechblender-speech-augmentation-framework","title":"SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generation","date":"2022-11-02","arxiv_id":"2211.00923","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/transformer-based-multi-aspect-multi","slug":"transformer-based-multi-aspect-multi","title":"Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment","date":"2022-05-06","arxiv_id":"2205.03432","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/speechocean762-an-open-source-non-native","slug":"speechocean762-an-open-source-non-native","title":"speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment","date":"2021-04-03","arxiv_id":"2104.01378","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"0826e4fe49e9fa80c2bd35d6771939b89ab30aa267fefc55089744f06202b2d7","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}