{"id":"https://openalex.org/W3015926140","doi":"https://doi.org/10.1109/icassp40776.2020.9054267","title":"LSTM-Based One-Pass Decoder for Low-Latency Streaming","display_name":"LSTM-Based One-Pass Decoder for Low-Latency Streaming","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015926140","doi":"https://doi.org/10.1109/icassp40776.2020.9054267","mag":"3015926140"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5019556388","display_name":"Javier Jorge","orcid":"https://orcid.org/0000-0002-9279-6768"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Javier Jorge","raw_affiliation_strings":["Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain","institution_ids":["https://openalex.org/I4210131846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101428553","display_name":"Adri\u00e0 Gim\u00e9nez","orcid":"https://orcid.org/0000-0002-3822-5526"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Adria Gimenez","raw_affiliation_strings":["Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain","institution_ids":["https://openalex.org/I4210131846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053563948","display_name":"Javier Iranzo-S\u00e1nchez","orcid":"https://orcid.org/0000-0002-4035-3295"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Iranzo-Sanchez","raw_affiliation_strings":["Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain","institution_ids":["https://openalex.org/I4210131846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006670076","display_name":"Joan Albert Silvestre-Cerd\u00e0","orcid":"https://orcid.org/0000-0003-2291-8296"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Joan Albert Silvestre-Cerda","raw_affiliation_strings":["Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain","institution_ids":["https://openalex.org/I4210131846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063036884","display_name":"Jorge Civera","orcid":"https://orcid.org/0000-0002-0963-0143"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jorge Civera","raw_affiliation_strings":["Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain","institution_ids":["https://openalex.org/I4210131846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054332728","display_name":"Albert Sanch\u00eds","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Albert Sanchis","raw_affiliation_strings":["Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain","institution_ids":["https://openalex.org/I4210131846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040605861","display_name":"Alfons Juan","orcid":"https://orcid.org/0000-0002-9984-4072"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alfons Juan","raw_affiliation_strings":["Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de València,Machine Learning and Language Processing (MLLP) research group, Valencian Research Institute for Artificial Intelligence,Spain","institution_ids":["https://openalex.org/I4210131846"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5019556388"],"corresponding_institution_ids":["https://openalex.org/I4210131846"],"apc_list":null,"apc_paid":null,"fwci":1.8558,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88255064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7814","last_page":"7818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9901000261306763,"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":0.8598936796188354},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.8071047067642212},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7109310030937195},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.6068720817565918},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5411306023597717},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.48303279280662537},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4234233498573303},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.36903703212738037},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.2113419473171234},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18850189447402954},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15308469533920288},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1260615885257721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8598936796188354},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8071047067642212},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7109310030937195},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.6068720817565918},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5411306023597717},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.48303279280662537},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4234233498573303},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36903703212738037},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2113419473171234},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18850189447402954},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15308469533920288},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1260615885257721},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:riunet.upv.es:10251/213949","is_oa":false,"landing_page_url":"http://hdl.handle.net/10251/213949","pdf_url":null,"source":{"id":"https://openalex.org/S4306401500","display_name":"RiuNet (Politechnical University of Valencia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W280003846","https://openalex.org/W1494108583","https://openalex.org/W1494198834","https://openalex.org/W1631260214","https://openalex.org/W1979625042","https://openalex.org/W1994536225","https://openalex.org/W2037942319","https://openalex.org/W2079735306","https://openalex.org/W2091981305","https://openalex.org/W2120861206","https://openalex.org/W2140539590","https://openalex.org/W2143195354","https://openalex.org/W2158069733","https://openalex.org/W2259472270","https://openalex.org/W2288502450","https://openalex.org/W2293185259","https://openalex.org/W2401969231","https://openalex.org/W2471933213","https://openalex.org/W2512608784","https://openalex.org/W2763120645","https://openalex.org/W2799473636","https://openalex.org/W2890817076","https://openalex.org/W2950797609","https://openalex.org/W2963451498","https://openalex.org/W2972528057","https://openalex.org/W3101648800","https://openalex.org/W6629717138","https://openalex.org/W6678040779","https://openalex.org/W6680663934","https://openalex.org/W6692563993","https://openalex.org/W6697157346","https://openalex.org/W6745635926"],"related_works":["https://openalex.org/W2585772085","https://openalex.org/W2510935666","https://openalex.org/W3097264971","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463"],"abstract_inverted_index":{"Current":[0],"state-of-the-art":[1],"models":[2],"based":[3],"on":[4],"Long-Short":[5],"Term":[6],"Memory":[7],"(LSTM)":[8],"networks":[9],"have":[10],"been":[11,96],"extensively":[12],"used":[13],"in":[14],"ASR":[15],"to":[16,30,57,67],"improve":[17],"performance.":[18],"However,":[19],"using":[20,78],"LSTMs":[21],"under":[22,100],"a":[23,38,44,75,79,84,101],"streaming":[24,40,103],"setup":[25],"is":[26],"not":[27],"straightforward":[28],"due":[29],"real-time":[31],"constraints.":[32],"In":[33],"this":[34],"paper":[35],"we":[36],"present":[37],"novel":[39],"decoder":[41],"that":[42,68],"includes":[43],"bidirectional":[45,85],"LSTM":[46,54,86,91],"acoustic":[47,87],"model":[48,56,88],"as":[49,51],"well":[50],"an":[52,70,90],"unidirectional":[53],"language":[55,92],"perform":[58,74],"the":[59,64,118],"decoding":[60,77],"efficiently":[61],"while":[62],"keeping":[63],"performance":[65],"comparable":[66],"of":[69],"off-line":[71],"setup.":[72],"We":[73,111],"one-pass":[76],"sliding":[80],"window":[81],"scheme":[82],"for":[83,117],"and":[89,98,105,114,121],"model.":[93],"This":[94],"has":[95],"implemented":[97],"assessed":[99],"pure":[102],"setup,":[104],"deployed":[106],"into":[107],"our":[108],"production":[109],"systems.":[110],"report":[112],"WER":[113,126],"latency":[115],"figures":[116],"well-known":[119],"LibriSpeech":[120],"TED-LIUM":[122],"tasks,":[123],"obtaining":[124],"competitive":[125],"results":[127],"with":[128],"low-latency":[129],"responses.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}