{"id":"https://openalex.org/W2944440087","doi":"https://doi.org/10.1109/iscslp.2018.8706581","title":"From Speech Signals to Semantics \u2014 Tagging Performance at Acoustic, Phonetic and Word Levels","display_name":"From Speech Signals to Semantics \u2014 Tagging Performance at Acoustic, Phonetic and Word Levels","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944440087","doi":"https://doi.org/10.1109/iscslp.2018.8706581","mag":"2944440087"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yao Qian","raw_affiliation_strings":["Educational Testing Service Research, USA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service Research, USA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030738204","display_name":"Rutuja Ubale","orcid":null},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rutuja Ubale","raw_affiliation_strings":["Educational Testing Service Research, USA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service Research, USA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029778136","display_name":"Patrick Lange","orcid":"https://orcid.org/0000-0003-3935-663X"},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Lange","raw_affiliation_strings":["Educational Testing Service Research, USA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service Research, USA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030816616","display_name":"Keelan Evanini","orcid":"https://orcid.org/0000-0003-4243-3376"},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keelan Evanini","raw_affiliation_strings":["Educational Testing Service Research, USA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service Research, USA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank Soong","raw_affiliation_strings":["Microsoft Research Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100342006"],"corresponding_institution_ids":["https://openalex.org/I1341030882"],"apc_list":null,"apc_paid":null,"fwci":0.9773,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82757561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"99","issue":null,"first_page":"280","last_page":"284"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.8680776357650757},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7190874218940735},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.569161057472229},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.563629150390625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5259026885032654},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5177125930786133},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5039896368980408},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4997732639312744},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48271700739860535},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4540097117424011},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.420251727104187},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08036074042320251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8680776357650757},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7190874218940735},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.569161057472229},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.563629150390625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5259026885032654},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5177125930786133},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5039896368980408},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4997732639312744},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48271700739860535},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4540097117424011},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.420251727104187},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08036074042320251},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/iscslp.2018.8706581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2049759087","https://openalex.org/W2064675550","https://openalex.org/W2094472029","https://openalex.org/W2099877156","https://openalex.org/W2102113734","https://openalex.org/W2114925438","https://openalex.org/W2117520332","https://openalex.org/W2132037657","https://openalex.org/W2137871902","https://openalex.org/W2150769028","https://openalex.org/W2155524666","https://openalex.org/W2160306971","https://openalex.org/W2327501763","https://openalex.org/W2400092632","https://openalex.org/W2510063686","https://openalex.org/W2515090196","https://openalex.org/W2550112318","https://openalex.org/W2786839803","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963288440","https://openalex.org/W2963311389","https://openalex.org/W2963571336","https://openalex.org/W6631362777","https://openalex.org/W6674796821","https://openalex.org/W6675365184","https://openalex.org/W6682600690","https://openalex.org/W6712742799","https://openalex.org/W6748263443"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2025614924","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W2559776840"],"abstract_inverted_index":{"Spoken":[0],"language":[1],"understanding":[2],"(SLU)":[3],"is":[4,54,75],"to":[5,77,89,122],"decode":[6],"the":[7,36,96,111,116],"semantic":[8,37],"information":[9],"embedded":[10],"in":[11,67],"speech":[12,61],"input.":[13],"SLU":[14],"decoding":[15],"can":[16,118],"be":[17,78,119],"significantly":[18],"degraded":[19],"by":[20,64],"mismatched":[21],"acoustic/language":[22],"models":[23],"between":[24],"training":[25],"and":[26,50,103],"testing":[27],"of":[28,40,110],"a":[29,57,68,107],"decoder.":[30],"In":[31],"this":[32],"paper":[33],"we":[34],"investigate":[35],"tagging":[38,73,98],"performance":[39,74],"bidirectional":[41],"LSTM":[42],"RNN":[43],"(BLSTM-RNN)":[44],"with":[45,95],"input":[46],"at":[47,100],"acoustic,":[48],"phonetic":[49],"word":[51,93],"levels.":[52],"It":[53],"tested":[55],"on":[56],"crowdsourced,":[58],"spoken":[59,63],"dialog":[60],"corpus":[62],"non-native":[65],"speakers":[66],"job":[69],"interview":[70],"task.":[71],"The":[72],"shown":[76],"improved":[79,121],"successively":[80],"from":[81],"low-level,":[82],"acoustic":[83],"MFCC,":[84],"midlevel,":[85],"stochastic":[86],"senone":[87],"posteriorgram,":[88],"high-level,":[90],"ASR":[91],"recognized":[92],"string,":[94],"corresponding":[97],"accuracies":[99],"70.6%,":[101],"82.1%":[102],"85.1%,":[104],"respectively.":[105],"With":[106],"score":[108],"fusion":[109],"three":[112],"individual":[113],"RNNs":[114],"together,":[115],"accuracy":[117],"further":[120],"87.0%.":[123]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}