{"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_with_a_benchmark_row":[{"paper":"/paper/conpco-preserving-phoneme-characteristics-for","title":"ConPCO: Preserving Phoneme Characteristics for Automatic Pronunciation Assessment Leveraging Contrastive Ordinal Regularization","date":"2024-06-05","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-self-supervised-learning-models","title":"Fine-Tuning Self-Supervised Learning Models for End-to-End Pronunciation Scoring","date":"2023-09-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-hierarchical-context-aware-modeling","title":"A Hierarchical Context-aware Modeling Approach for Multi-aspect and Multi-granular Pronunciation Assessment","date":"2023-05-29","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/hierarchical-pronunciation-assessment-with","title":"Hierarchical Pronunciation Assessment with Multi-Aspect Attention","date":"2022-11-15","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/speechblender-speech-augmentation-framework","title":"SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generation","date":"2022-11-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/transformer-based-multi-aspect-multi","title":"Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment","date":"2022-05-06","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/speechocean762-an-open-source-non-native","title":"speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment","date":"2021-04-03","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."}