{"id":"https://openalex.org/W4402112517","doi":"https://doi.org/10.21437/interspeech.2024-2157","title":"On Disfluency and Non-lexical Sound Labeling for End-to-end Automatic Speech Recognition","display_name":"On Disfluency and Non-lexical Sound Labeling for End-to-end Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112517","doi":"https://doi.org/10.21437/interspeech.2024-2157"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2157","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2157","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/A5020514527","display_name":"P\u00e9ter Mihajlik","orcid":"https://orcid.org/0000-0001-7532-9773"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Mihajlik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104668516","display_name":"Yan Meng","orcid":"https://orcid.org/0000-0001-5280-6653"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113034319","display_name":"M\u00e1t\u00e9 Soma K\u00e1d\u00e1r","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mate S Kadar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085707341","display_name":"Julian Linke","orcid":"https://orcid.org/0009-0002-9904-0944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian Linke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027851634","display_name":"Barbara Schuppler","orcid":"https://orcid.org/0000-0003-4009-0832"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barbara Schuppler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070593335","display_name":"Katalin M\u00e1dy","orcid":"https://orcid.org/0000-0002-4968-7849"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katalin M\u00e1dy","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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1270","last_page":"1274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9886999726295471,"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":0.9886999726295471,"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":0.98580002784729,"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/T11309","display_name":"Music and Audio Processing","score":0.9320999979972839,"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/computer-science","display_name":"Computer science","score":0.6821293234825134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6257427930831909},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.622199535369873},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.4680960178375244},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.430019736289978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35761553049087524},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3507978916168213},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29452580213546753},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.054582953453063965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6821293234825134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6257427930831909},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.622199535369873},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.4680960178375244},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.430019736289978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35761553049087524},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3507978916168213},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29452580213546753},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.054582953453063965}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-2157","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2157","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/W4396816926","https://openalex.org/W2593532750","https://openalex.org/W3207232378","https://openalex.org/W2642467014","https://openalex.org/W2889523925","https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W2171620991","https://openalex.org/W4281389974","https://openalex.org/W2131711534"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
