{"id":"https://openalex.org/W4402111997","doi":"https://doi.org/10.21437/interspeech.2024-869","title":"Contextual Biasing with Confidence-based Homophone Detector for Mandarin End-to-End Speech Recognition","display_name":"Contextual Biasing with Confidence-based Homophone Detector for Mandarin End-to-End Speech Recognition","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111997","doi":"https://doi.org/10.21437/interspeech.2024-869"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-869","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107601103","display_name":"Chengxu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengxu Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102892107","display_name":"Zheng Lin","orcid":"https://orcid.org/0000-0001-6909-5421"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012921233","display_name":"Sanli Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanli Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072887461","display_name":"Gaofeng Cheng","orcid":"https://orcid.org/0000-0002-2102-6061"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaofeng Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113361552","display_name":"Sujie Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sujie Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052454197","display_name":"Li Ta","orcid":"https://orcid.org/0000-0001-5431-9787"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ta Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"747","last_page":"751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9153000116348267,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/homophone","display_name":"Homophone","score":0.8038033843040466},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6675657629966736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6139515042304993},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5745549201965332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5489169359207153},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4807600677013397},{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.4148930609226227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2981310486793518},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20983362197875977},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19771316647529602},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.16520869731903076},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15112686157226562},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1460508406162262}],"concepts":[{"id":"https://openalex.org/C160253069","wikidata":"https://www.wikidata.org/wiki/Q221079","display_name":"Homophone","level":2,"score":0.8038033843040466},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6675657629966736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6139515042304993},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5745549201965332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5489169359207153},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4807600677013397},{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.4148930609226227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2981310486793518},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20983362197875977},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19771316647529602},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.16520869731903076},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15112686157226562},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1460508406162262},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-869","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4099999964237213,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2358775429","https://openalex.org/W1567440624","https://openalex.org/W2364211260","https://openalex.org/W1977345729","https://openalex.org/W2105439214","https://openalex.org/W2079548008","https://openalex.org/W2030399736","https://openalex.org/W1985374210","https://openalex.org/W4245032792","https://openalex.org/W2371388421"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
