{"id":"https://openalex.org/W4402112292","doi":"https://doi.org/10.21437/interspeech.2024-1853","title":"Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study","display_name":"Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112292","doi":"https://doi.org/10.21437/interspeech.2024-1853"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1853","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1853","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":"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/A5025104497","display_name":"Peikun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Peikun Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017369100","display_name":"Sining Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sining Sun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042775692","display_name":"Changhao Shan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changhao Shan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113804918","display_name":"Qing Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066505495","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0003-1442-6785"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025104497"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66172835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4468","last_page":"4472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9653000235557556,"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":0.9653000235557556,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7849828004837036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7672964334487915},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48912912607192993},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.48521116375923157},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4267701804637909},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4173932373523712},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.41100606322288513},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3321692943572998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.328056275844574},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0794174075126648}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7849828004837036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7672964334487915},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48912912607192993},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.48521116375923157},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4267701804637909},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4173932373523712},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.41100606322288513},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3321692943572998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.328056275844574},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0794174075126648}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1853","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1853","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2154415461","https://openalex.org/W1911859126","https://openalex.org/W642007152","https://openalex.org/W46679383","https://openalex.org/W2056066842","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2550171623"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
