{"id":"https://openalex.org/W4417073230","doi":"https://doi.org/10.1145/3743093.3771018","title":"Zero-Shot Speech Recognition from Text-Only Data through Synthesized Spectrogram Refinement Using Style Truncation and Contextual Alignment Loss","display_name":"Zero-Shot Speech Recognition from Text-Only Data through Synthesized Spectrogram Refinement Using Style Truncation and Contextual Alignment Loss","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073230","doi":"https://doi.org/10.1145/3743093.3771018"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771018","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3771018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","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":null,"display_name":"Yuan Li","orcid":"https://orcid.org/0009-0003-0802-9203"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Huhhot, China; National &amp; Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Huhhot, China and Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Huhhot, China"],"raw_orcid":"https://orcid.org/0009-0003-0802-9203","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Huhhot, China; National &amp; Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Huhhot, China and Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Huhhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008226894","display_name":"Yonghe Wang","orcid":"https://orcid.org/0000-0003-1647-1539"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghe Wang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Huhhot, China; National &amp; Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Huhhot, China and Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Huhhot, China"],"raw_orcid":"https://orcid.org/0000-0003-1647-1539","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Huhhot, China; National &amp; Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Huhhot, China and Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Huhhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113373769","display_name":"Zhenjie Gao","orcid":"https://orcid.org/0009-0002-6287-2472"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjie Gao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Huhhot, China; National &amp; Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Huhhot, China and Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Huhhot, China"],"raw_orcid":"https://orcid.org/0009-0002-6287-2472","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Huhhot, China; National &amp; Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Huhhot, China and Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Huhhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Huhhot, China; National &amp; Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Huhhot, China and Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Huhhot, China"],"raw_orcid":"https://orcid.org/0000-0001-7312-1629","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Huhhot, China; National &amp; Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Huhhot, China and Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Huhhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5397999882698059,"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":0.5397999882698059,"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":0.3684000074863434,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.01899999938905239,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7760999798774719},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.5011000037193298},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39430001378059387},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.36090001463890076},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.3253999948501587}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7760999798774719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6826000213623047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6657999753952026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5013999938964844},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32269999384880066},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27300000190734863}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3771018","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3771018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4486119710","display_name":null,"funder_award_id":"2025MS06001","funder_id":"https://openalex.org/F4320322868","funder_display_name":"Natural Science Foundation of Inner Mongolia"},{"id":"https://openalex.org/G8066327701","display_name":null,"funder_award_id":"62566045, 62366037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322868","display_name":"Natural Science Foundation of Inner Mongolia","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2476548250","https://openalex.org/W2985368596","https://openalex.org/W2995181338","https://openalex.org/W3004059350","https://openalex.org/W3011573842","https://openalex.org/W3100460087","https://openalex.org/W3162293946","https://openalex.org/W3166426964","https://openalex.org/W3170204166","https://openalex.org/W3194921972","https://openalex.org/W3209059054","https://openalex.org/W4210774711","https://openalex.org/W4213457947","https://openalex.org/W4224930731","https://openalex.org/W4297841232","https://openalex.org/W4372260611","https://openalex.org/W4385571829","https://openalex.org/W4386591026","https://openalex.org/W4386813775","https://openalex.org/W4389524053","https://openalex.org/W4392904149","https://openalex.org/W4392904154","https://openalex.org/W4399593307","https://openalex.org/W4402187093","https://openalex.org/W4403653940","https://openalex.org/W4416955811"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-06T00:00:00"}
