{"id":"https://openalex.org/W3198763610","doi":"https://doi.org/10.21437/interspeech.2021-1449","title":"Real-Time End-to-End Monaural Multi-Speaker Speech Recognition","display_name":"Real-Time End-to-End Monaural Multi-Speaker Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198763610","doi":"https://doi.org/10.21437/interspeech.2021-1449","mag":"3198763610"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1449","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5002404808","display_name":"Li Song","orcid":"https://orcid.org/0000-0002-7124-5182"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066579310","display_name":"Beibei Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beibei Ouyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090944758","display_name":"Fuchuan Tong","orcid":"https://orcid.org/0000-0001-5123-1843"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuchuan Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039844745","display_name":"Dexin Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dexin Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103050255","display_name":"Lin Li","orcid":"https://orcid.org/0000-0002-5021-2648"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyang Hong","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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3750","last_page":"3754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/monaural","display_name":"Monaural","score":0.8554078340530396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.755304753780365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7509796023368835},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6510763168334961},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6105382442474365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23144182562828064}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8554078340530396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755304753780365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7509796023368835},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6510763168334961},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6105382442474365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23144182562828064}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1449","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":14,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W2031647436","https://openalex.org/W2107252982","https://openalex.org/W2127141656","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2792764867","https://openalex.org/W2890244912","https://openalex.org/W2892009249","https://openalex.org/W2962715207","https://openalex.org/W2963341956","https://openalex.org/W2963477857","https://openalex.org/W3011129471","https://openalex.org/W3025165719"],"related_works":["https://openalex.org/W2401567014","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}