{"id":"https://openalex.org/W1983205135","doi":"https://doi.org/10.1109/slt.2014.7078631","title":"Online word-spotting in continuous speech with recurrent neural networks","display_name":"Online word-spotting in continuous speech with recurrent neural networks","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1983205135","doi":"https://doi.org/10.1109/slt.2014.7078631","mag":"1983205135"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5007389429","display_name":"Pallavi Baljekar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pallavi Baljekar","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Disney Research, Pittsburgh"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Disney Research, Pittsburgh","institution_ids":["https://openalex.org/I4210142140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075945110","display_name":"Jill Fain Lehman","orcid":"https://orcid.org/0000-0001-7906-4899"},"institutions":[{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jill Fain Lehman","raw_affiliation_strings":["Disney Research, Pittsburgh"],"affiliations":[{"raw_affiliation_string":"Disney Research, Pittsburgh","institution_ids":["https://openalex.org/I4210142140"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102775511","display_name":"Rita Singh","orcid":"https://orcid.org/0000-0003-3743-0162"},"institutions":[{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rita Singh","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Disney Research, Pittsburgh"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Disney Research, Pittsburgh","institution_ids":["https://openalex.org/I4210142140"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007389429"],"corresponding_institution_ids":["https://openalex.org/I4210142140","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.8631,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.91673675,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"536","last_page":"541"},"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":0.9973999857902527,"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":0.9965000152587891,"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":0.8476375341415405},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8321869373321533},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7831814289093018},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7239043712615967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5812596678733826},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5736639499664307},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5688188672065735},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5583437085151672},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5578845739364624},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5439325571060181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5005331039428711},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4224727749824524},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4209819436073303},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38408294320106506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8476375341415405},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8321869373321533},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7831814289093018},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7239043712615967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5812596678733826},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5736639499664307},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5688188672065735},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5583437085151672},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5578845739364624},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5439325571060181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5005331039428711},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4224727749824524},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4209819436073303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38408294320106506},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2014.7078631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1487889217","https://openalex.org/W1506255978","https://openalex.org/W1553469512","https://openalex.org/W1899504021","https://openalex.org/W2053831280","https://openalex.org/W2103359087","https://openalex.org/W2119689163","https://openalex.org/W2122797512","https://openalex.org/W2127141656","https://openalex.org/W2131774270","https://openalex.org/W2143612262","https://openalex.org/W2171019095","https://openalex.org/W2403141126","https://openalex.org/W6630319106","https://openalex.org/W6631636882","https://openalex.org/W6664008549","https://openalex.org/W6675321185","https://openalex.org/W6712744878"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2388033618","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W1969408022","https://openalex.org/W2000885660"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"introduce":[4],"a":[5,40,44,79,101,115],"simplified":[6],"architecture":[7,81],"for":[8,34],"gated":[9],"recurrent":[10],"neural":[11],"networks":[12,57,87],"that":[13,121],"can":[14],"be":[15,24],"used":[16,88],"in":[17,26,43,89],"single-pass":[18],"applications,":[19],"where":[20,60],"word-spotting":[21],"needs":[22],"to":[23,48,84,97],"done":[25],"real-time":[27],"and":[28,72,108],"phoneme-level":[29],"information":[30],"is":[31,64],"not":[32],"available":[33],"training.":[35],"The":[36],"network":[37,77],"operates":[38],"as":[39,82],"self-contained":[41],"block":[42],"strictly":[45],"forward-pass":[46],"configuration":[47],"directly":[49],"generate":[50],"keyword":[51,90,118],"labels.":[52],"We":[53],"call":[54],"these":[55,122],"simple":[56],"causal":[58],"networks,":[59,123],"the":[61,68,69,75,106],"current":[62],"output":[63],"only":[65],"weighted":[66],"by":[67],"past":[70],"inputs":[71],"outputs.":[73],"Since":[74],"basic":[76],"has":[78],"simpler":[80],"compared":[83],"traditional":[85],"memory":[86],"spotting,":[91],"it":[92],"also":[93],"requires":[94],"less":[95],"data":[96],"train.":[98],"Experiments":[99],"on":[100],"standard":[102,116],"speech":[103],"database":[104],"highlight":[105],"behavior":[107],"efficacy":[109],"of":[110],"such":[111],"networks.":[112],"Comparisons":[113],"with":[114],"HMM-based":[117],"spotter":[119],"show":[120],"while":[124],"simple,":[125],"are":[126],"still":[127],"more":[128],"accurate.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}