{"id":"https://openalex.org/W4385822357","doi":"https://doi.org/10.21437/interspeech.2023-486","title":"Streaming Speech-to-Confusion Network Speech Recognition","display_name":"Streaming Speech-to-Confusion Network Speech Recognition","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822357","doi":"https://doi.org/10.21437/interspeech.2023-486"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-486","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5017041805","display_name":"Denis Filimonov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Denis Filimonov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101330599","display_name":"Prabhat Pandey","orcid":"https://orcid.org/0000-0003-0267-751X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prabhat Pandey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ariya Rastrow","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014054572","display_name":"Ankur Gandhe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankur Gandhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4099","last_page":"4103"},"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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":0.8281733989715576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7366113662719727},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7253460884094238},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6594691872596741},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.6505678296089172},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6240841150283813},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.572996973991394},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.546920120716095},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45453977584838867},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4337530732154846},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4216557741165161},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42119792103767395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37075677514076233},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.25570595264434814},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07789245247840881}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281733989715576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7366113662719727},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7253460884094238},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6594691872596741},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.6505678296089172},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6240841150283813},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.572996973991394},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.546920120716095},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45453977584838867},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4337530732154846},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4216557741165161},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42119792103767395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37075677514076233},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25570595264434814},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07789245247840881},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-486","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1828163288","https://openalex.org/W2134741316","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2594610113","https://openalex.org/W2913718171","https://openalex.org/W2981696585","https://openalex.org/W3015457435","https://openalex.org/W3015671919","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3096702180","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3148654612","https://openalex.org/W3161375121","https://openalex.org/W3163907627","https://openalex.org/W4224918838","https://openalex.org/W4296068786","https://openalex.org/W4297841914","https://openalex.org/W4319862426","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W151018310","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W4385611764","https://openalex.org/W2519224033"],"abstract_inverted_index":{"In":[0],"interactive":[1,47],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"systems,":[6],"low-latency":[7],"requirements":[8],"limit":[9],"the":[10,65,80],"amount":[11],"of":[12,53],"search":[13],"space":[14],"that":[15,35,50,85],"can":[16],"be":[17],"explored":[18],"during":[19],"decoding,":[20],"particularly":[21],"in":[22],"end-to-end":[23],"neural":[24],"ASR.In":[25],"this":[26],"paper,":[27],"we":[28],"present":[29],"a":[30,37,60,89,94],"novel":[31],"streaming":[32],"ASR":[33],"architecture":[34],"outputs":[36],"confusion":[38],"network":[39],"while":[40,64],"maintaining":[41],"limited":[42],"latency,":[43],"as":[44],"needed":[45],"for":[46],"applications.We":[48],"show":[49,84],"1-best":[51],"results":[52],"our":[54,86],"model":[55,87],"are":[56],"on":[57,79,93],"par":[58],"with":[59],"comparable":[61],"RNN-T":[62,91],"system,":[63],"richer":[66],"hypothesis":[67],"set":[68],"allows":[69],"secondpass":[70],"rescoring":[71],"to":[72],"achieve":[73],"10-20%":[74],"lower":[75],"word":[76],"error":[77],"rate":[78],"LibriSpeech":[81],"task.We":[82],"also":[83],"outperforms":[88],"strong":[90],"baseline":[92],"far-field":[95],"voice":[96],"assistant":[97],"task.":[98]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
