{"id":"https://openalex.org/W4415433948","doi":"https://doi.org/10.21437/interspeech.2025-511","title":"Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding","display_name":"Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433948","doi":"https://doi.org/10.21437/interspeech.2025-511"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-511","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","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/A5069159378","display_name":"Haoran Zhou","orcid":"https://orcid.org/0000-0002-3530-0500"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haoran Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074833963","display_name":"Xingchen Song","orcid":"https://orcid.org/0009-0009-9516-5361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingchen Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029494437","display_name":"Brendan Fahy","orcid":"https://orcid.org/0000-0001-9344-1590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brendan Fahy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082930506","display_name":"Qiaochu Song","orcid":"https://orcid.org/0009-0003-8842-5416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiaochu Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449712","display_name":"Binbin Zhang","orcid":"https://orcid.org/0000-0002-1874-1881"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binbin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041630666","display_name":"Zhendong Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhendong Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069978153","display_name":"Anshul Wadhawan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anshul Wadhawan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046534669","display_name":"Denglin Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Denglin Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065759951","display_name":"Apurv Verma","orcid":"https://orcid.org/0000-0002-1009-7032"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Apurv Verma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Vinay Ramesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vinay Ramesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076366468","display_name":"S. Prasad","orcid":"https://orcid.org/0000-0003-3976-5839"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srivas Prasad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111881770","display_name":"Michele Franceschini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michele M. Franceschini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5069159378"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35687296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4428","last_page":"4432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9861000180244446,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9861000180244446,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9660000205039978,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9491000175476074,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/decoding-methods","display_name":"Decoding methods","score":0.6256999969482422},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.40849998593330383},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2939000129699707},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.2935999929904938},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.28940001130104065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760699987411499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6359000205993652},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6256999969482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42160001397132874},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.40849998593330383},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-511","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-24T00:00:00"}