{"id":"https://openalex.org/W4402112450","doi":"https://doi.org/10.21437/interspeech.2024-258","title":"Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer","display_name":"Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112450","doi":"https://doi.org/10.21437/interspeech.2024-258"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-258","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-258","pdf_url":"https://www.isca-archive.org/interspeech_2024/honda24_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/honda24_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114218718","display_name":"Tomoki Honda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Honda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110763152","display_name":"Shinsuke Sakai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinsuke Sakai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","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":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2895","last_page":"2899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9957000017166138,"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/T10320","display_name":"Neural Networks and Applications","score":0.9690999984741211,"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":0.7345669269561768},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6811860799789429},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.6043733954429626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42835530638694763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3554643392562866},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2793131470680237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7345669269561768},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6811860799789429},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.6043733954429626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42835530638694763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3554643392562866},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2793131470680237},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-258","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-258","pdf_url":"https://www.isca-archive.org/interspeech_2024/honda24_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.04159","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.04159","pdf_url":"https://arxiv.org/pdf/2410.04159","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-258","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-258","pdf_url":"https://www.isca-archive.org/interspeech_2024/honda24_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112450.pdf","grobid_xml":"https://content.openalex.org/works/W4402112450.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382566571","https://openalex.org/W4396696052","https://openalex.org/W4402327032"],"abstract_inverted_index":{"Recently,":[0],"Conformer":[1],"has":[2],"achieved":[3],"state-of-the-art":[4],"performance":[5],"in":[6,106,111,117,129,133],"many":[7],"speech":[8],"recognition":[9,89],"tasks.However,":[10],"the":[11,24,30,33,37,41,58,134],"Transformer-based":[12],"models":[13],"show":[14,102],"significant":[15,115],"deterioration":[16],"for":[17,63],"long-form":[18,67,91],"speech,":[19],"such":[20],"as":[21],"lectures,":[22],"because":[23],"self-attention":[25,60],"mechanism":[26],"becomes":[27],"unreliable":[28],"with":[29,69],"computation":[31],"of":[32,36,47,66,77,90,97,125],"square":[34],"order":[35],"input":[38],"length.To":[39],"solve":[40],"problem,":[42],"we":[43,93],"incorporate":[44],"a":[45,70,95,122],"kind":[46],"state-space":[48],"model,":[49],"Hungry":[50,51],"Hippos":[52],"(H3),":[53],"to":[54],"replace":[55],"or":[56],"complement":[57],"multi-head":[59],"(MHSA).H3":[61],"allows":[62],"efficient":[64,86],"modeling":[65],"sequences":[68],"linear-order":[71],"computation.In":[72],"experiments":[73],"using":[74,104],"two":[75],"datasets":[76],"CSJ":[78],"and":[79,87,99,101,109,127],"LibriSpeech,":[80],"our":[81],"proposed":[82],"H3-Conformer":[83],"model":[84],"performs":[85],"robust":[88],"speech.Moreover,":[92],"propose":[94],"hybrid":[96],"H3":[98,105,126],"MHSA":[100,110,128],"that":[103],"higher":[107],"layers":[108,113],"lower":[112],"provides":[114],"improvement":[116],"online":[118],"recognition.We":[119],"also":[120],"investigate":[121],"parallel":[123],"use":[124],"all":[130],"layers,":[131],"resulting":[132],"best":[135],"performance.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}