{"url":"/task/polyphone-disambiguation","name":"Polyphone disambiguation","slug":"polyphone-disambiguation","description_markdown":"A part of the TTS-front end framework which serves to predict the correct pronunciation for the input polyphone characters.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":15,"papers_with_code":3,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/polyphone-disambiguation-on-cpp","slug":"polyphone-disambiguation-on-cpp","dataset":"CPP","dataset_url":"/dataset/cpp","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"g2pW","paper_title":"g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin","paper_url":"/paper/g2pw-a-conditional-weighted-softmax-bert-for","paper_date":"2022-03-20","arxiv_id":"2203.10430","code_links":[{"title":"GitYCC/g2pW","url":"https://github.com/GitYCC/g2pW"}],"syntology":null}}],"datasets":[{"url":"/dataset/cpp","name":"CPP","full_name":"Chinese Polyphones with Pinyin","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":3,"of":3,"tagged_in_all":15,"items":[{"url":"/paper/dict-tts-learning-to-pronounce-with-prior","title":"Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech","date":"2022-06-05","arxiv_id":"2206.02147","repositories_listed":1,"syntology":null},{"url":"/paper/g2pw-a-conditional-weighted-softmax-bert-for","title":"g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin","date":"2022-03-20","arxiv_id":"2203.10430","repositories_listed":1,"syntology":null},{"url":"/paper/g2pm-a-neural-grapheme-to-phoneme-conversion","title":"g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset","date":"2020-04-07","arxiv_id":"2004.03136","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}