{"id":"https://openalex.org/W2729190387","doi":"https://doi.org/10.1109/lsp.2017.2723507","title":"Low Latency Acoustic Modeling Using Temporal Convolution and LSTMs","display_name":"Low Latency Acoustic Modeling Using Temporal Convolution and LSTMs","publication_year":2017,"publication_date":"2017-07-04","ids":{"openalex":"https://openalex.org/W2729190387","doi":"https://doi.org/10.1109/lsp.2017.2723507","mag":"2729190387"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2017.2723507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2017.2723507","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5081105332","display_name":"Vijayaditya Peddinti","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vijayaditya Peddinti","raw_affiliation_strings":["Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377935","display_name":"Yiming Wang","orcid":"https://orcid.org/0000-0002-5932-4371"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081105332"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":22.4326,"has_fulltext":false,"cited_by_count":175,"citation_normalized_percentile":{"value":0.99523753,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"25","issue":"3","first_page":"373","last_page":"377"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.8189796805381775},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7635581493377686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6913736462593079},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6652319431304932},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5697591304779053},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5484914183616638},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5461449027061462},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4686205983161926},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.463069349527359},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.4339224398136139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3190142512321472},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05970385670661926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189796805381775},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7635581493377686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6913736462593079},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6652319431304932},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5697591304779053},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5484914183616638},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5461449027061462},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4686205983161926},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.463069349527359},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.4339224398136139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3190142512321472},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05970385670661926},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2017.2723507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2017.2723507","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2488603923","display_name":null,"funder_award_id":"2012-12050800010","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"}],"funders":[{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W973008471","https://openalex.org/W1424447973","https://openalex.org/W1489125746","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1566256432","https://openalex.org/W1569447338","https://openalex.org/W1600744878","https://openalex.org/W2005708641","https://openalex.org/W2018970719","https://openalex.org/W2117671523","https://openalex.org/W2125336414","https://openalex.org/W2131774270","https://openalex.org/W2193413348","https://openalex.org/W2288502450","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2329068866","https://openalex.org/W2397424575","https://openalex.org/W2402146185","https://openalex.org/W2510616059","https://openalex.org/W2512608784","https://openalex.org/W2514741789","https://openalex.org/W2515439472","https://openalex.org/W2631415506","https://openalex.org/W2747135936","https://openalex.org/W2963795358","https://openalex.org/W2963920996","https://openalex.org/W2964084166","https://openalex.org/W6628438334","https://openalex.org/W6629052376","https://openalex.org/W6631362777","https://openalex.org/W6633847657","https://openalex.org/W6633947590","https://openalex.org/W6687566353","https://openalex.org/W6696934422","https://openalex.org/W6712930963"],"related_works":["https://openalex.org/W2357191878","https://openalex.org/W1997078944","https://openalex.org/W1968065688","https://openalex.org/W1552846815","https://openalex.org/W2142945567","https://openalex.org/W2030332364","https://openalex.org/W2005459225","https://openalex.org/W4289829835","https://openalex.org/W4220830676","https://openalex.org/W2004851054"],"abstract_inverted_index":{"Bidirectional":[0],"long":[1],"short-term":[2],"memory":[3],"(BLSTM)":[4],"acoustic":[5,36,100],"models":[6,37,101],"provide":[7],"a":[8],"significant":[9],"word":[10],"error":[11],"rate":[12,90,124],"reduction":[13],"compared":[14],"to":[15,33,43,72,76,84,120],"their":[16],"unidirectional":[17,69],"counterpart,":[18],"as":[19],"they":[20],"model":[21,117],"both":[22],"the":[23,53,59,74,86,115,130,137,142],"past":[24],"and":[25,112,136],"future":[26],"temporal":[27,56],"contexts.":[28],"However,":[29],"it":[30],"is":[31],"nontrivial":[32],"deploy":[34],"bidirectional":[35],"for":[38],"online":[39],"speech":[40],"recognition":[41],"due":[42],"an":[44],"increase":[45],"in":[46,58,141],"latency.":[47],"In":[48],"this":[49],"letter,":[50],"we":[51],"propose":[52],"use":[54],"of":[55,61],"convolution,":[57],"form":[60],"time-delay":[62],"neural":[63],"network":[64],"(TDNN)":[65],"layers,":[66],"along":[67],"with":[68],"LSTM":[70],"layers":[71,111],"limit":[73],"latency":[75],"200":[77],"ms.":[78],"This":[79],"architecture":[80],"has":[81],"been":[82],"shown":[83],"outperform":[85],"state-of-the-art":[87],"low":[88],"frame":[89,107,123],"(LFR)":[91],"BLSTM":[92,99],"models.":[93],"We":[94,126],"further":[95],"improve":[96],"these":[97,121],"LFR":[98],"by":[102],"operating":[103],"them":[104],"at":[105,109],"higher":[106],"rates":[108],"lower":[110],"show":[113],"that":[114],"proposed":[116],"performs":[118],"similar":[119],"mixed":[122],"BLSTMs.":[125],"present":[127],"results":[128],"on":[129],"Switchboard":[131],"300":[132],"h":[133],"LVCSR":[134,139],"task":[135],"AMI":[138],"task,":[140],"three":[143],"microphone":[144],"conditions.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":39},{"year":2018,"cited_by_count":43}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}