{"id":"https://openalex.org/W2746785844","doi":"https://doi.org/10.21437/interspeech.2017-590","title":"Minimum Semantic Error Cost Training of Deep Long Short-Term Memory Networks for Topic Spotting on Conversational Speech","display_name":"Minimum Semantic Error Cost Training of Deep Long Short-Term Memory Networks for Topic Spotting on Conversational Speech","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2746785844","doi":"https://doi.org/10.21437/interspeech.2017-590","mag":"2746785844"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-590","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhong Meng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070867959","display_name":"Biing\u2010Hwang Juang","orcid":"https://orcid.org/0000-0002-5773-5679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biing-Hwang Juang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101749753"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.195,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61806644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2496","last_page":"2500"},"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":0.9993000030517578,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8622064590454102},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7741439342498779},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6409434080123901},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6063459515571594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5981929898262024},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5760699510574341},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5478435158729553},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.540276825428009},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5200381278991699},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49900126457214355},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.44321537017822266},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3799394369125366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8622064590454102},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7741439342498779},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6409434080123901},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6063459515571594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5981929898262024},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5760699510574341},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5478435158729553},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.540276825428009},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5200381278991699},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49900126457214355},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.44321537017822266},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3799394369125366},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-590","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W14913773","https://openalex.org/W854541894","https://openalex.org/W1498731359","https://openalex.org/W1561056154","https://openalex.org/W1877570817","https://openalex.org/W1978394996","https://openalex.org/W1979904744","https://openalex.org/W1980317488","https://openalex.org/W2005708641","https://openalex.org/W2033565080","https://openalex.org/W2063224314","https://openalex.org/W2085628288","https://openalex.org/W2115730999","https://openalex.org/W2125234026","https://openalex.org/W2131342762","https://openalex.org/W2141599568","https://openalex.org/W2143612262","https://openalex.org/W2147152072","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2161195767","https://openalex.org/W2171144711","https://openalex.org/W2193413348","https://openalex.org/W2293634267","https://openalex.org/W2509658457","https://openalex.org/W2636483419","https://openalex.org/W2748717988"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"The":[0,100,141],"topic":[1,74,147],"spotting":[2,75],"performance":[3],"on":[4,25,92,158],"spontaneous":[5],"conversational":[6],"speech":[7,36],"can":[8],"be":[9],"significantly":[10],"improved":[11],"by":[12],"operating":[13],"a":[14,19,51],"support":[15],"vector":[16],"machine":[17],"with":[18,76,156],"latent":[20,111],"semantic":[21,45,84,102,112,133],"rational":[22],"kernel":[23],"(LSRK)":[24],"the":[26,35,43,79,82,93,98,110,121,131,137,152],"decoded":[27],"word":[28,90,117,139],"lattices":[29,64,94],"(i.e.,":[30],"weighted":[31],"finite-state":[32],"transducers)":[33],"of":[34,50,87,136],"[1].":[37],"In":[38],"this":[39],"work,":[40],"we":[41],"propose":[42],"minimum":[44],"error":[46,85,103,134],"cost":[47,86,104,135],"(MSEC)":[48],"training":[49],"deep":[52],"bidirectional":[53],"long":[54],"short-term":[55],"memory":[56],"(BLSTM)-hidden":[57],"Markov":[58],"model":[59,61],"acoustic":[60],"for":[62,73],"generating":[63],"that":[65],"are":[66,70],"semantically":[67],"accurate":[68],"and":[69,125],"better":[71],"suited":[72],"LSRK.":[77],"With":[78],"MSEC":[80],"training,":[81],"expected":[83,132],"all":[88],"possible":[89],"sequences":[91],"is":[95,105,126],"minimized":[96],"given":[97],"reference.":[99],"word-word":[101],"first":[106],"computed":[107],"from":[108,120],"either":[109],"analysis":[113],"or":[114],"distributed":[115],"vector-space":[116],"representations":[118],"learned":[119],"recurrent":[122],"neural":[123],"networks":[124],"then":[127],"accumulated":[128],"to":[129],"form":[130],"hypothesized":[138],"sequences.":[140],"proposed":[142],"method":[143],"achieves":[144],"3.5%-4.5%":[145],"absolute":[146],"classification":[148],"accuracy":[149],"improvement":[150],"over":[151],"baseline":[153],"BLSTM":[154],"trained":[155],"cross-entropy":[157],"Switchboard-1":[159],"Release":[160],"2":[161],"dataset.":[162]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}