{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/multimodal-neural-pronunciation-modeling-for","title":"Multimodal neural pronunciation modeling for spoken languages with logographic origin","arxiv_id":"1809.04203","date":"2018-09-12","proceeding":"EMNLP 2018 10","authors":["Minh Nguyen","Gia H. Ngo","Nancy F. Chen"],"abstract":"Graphemes of most languages encode pronunciation, though some are more\nexplicit than others. Languages like Spanish have a straightforward mapping\nbetween its graphemes and phonemes, while this mapping is more convoluted for\nlanguages like English. Spoken languages such as Cantonese present even more\nchallenges in pronunciation modeling: (1) they do not have a standard written\nform, (2) the closest graphemic origins are logographic Han characters, of\nwhich only a subset of these logographic characters implicitly encodes\npronunciation. In this work, we propose a multimodal approach to predict the\npronunciation of Cantonese logographic characters, using neural networks with a\ngeometric representation of logographs and pronunciation of cognates in\nhistorically related languages. The proposed framework improves performance by\n18.1% and 25.0% respective to unimodal and multimodal baselines.","url_abs":"http://arxiv.org/abs/1809.04203v1","url_pdf":"http://arxiv.org/pdf/1809.04203v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multimodal-neural-pronunciation-modeling-for","repo_url":"https://github.com/mnhng/logographic","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}