{"id":"https://openalex.org/W177307080","doi":"https://doi.org/10.21437/interspeech.2005-695","title":"Using MLP features in SRI's conversational speech recognition system","display_name":"Using MLP features in SRI's conversational speech recognition system","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W177307080","doi":"https://doi.org/10.21437/interspeech.2005-695","mag":"177307080"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-695","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5101999009","display_name":"Qifeng Zhu","orcid":"https://orcid.org/0000-0002-5303-9924"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qifeng Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021511902","display_name":"Barry Y. Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barry Y. Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112003894","display_name":"Nelson Morgan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nelson Morgan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101999009"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.3544,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.9916169,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2141","last_page":"2144"},"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":0.9988999962806702,"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":0.994700014591217,"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/speech-recognition","display_name":"Speech recognition","score":0.7906572818756104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7622997760772705},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.6053594350814819},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5742019414901733},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5395175218582153},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5341023206710815},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5338847041130066},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5083896517753601},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.497055321931839},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4789595901966095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47166454792022705},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.467218279838562},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4404821991920471},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.43934351205825806},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31302958726882935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.082421213388443}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7906572818756104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622997760772705},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.6053594350814819},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5742019414901733},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5395175218582153},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5341023206710815},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5338847041130066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5083896517753601},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.497055321931839},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4789595901966095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47166454792022705},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.467218279838562},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4404821991920471},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.43934351205825806},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31302958726882935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.082421213388443},{"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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2005-695","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.969","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-speech.sri.com/cgi-bin/run-distill?papers/eurospeech2005-mlp-cts.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.5140","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.5140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ftp.icsi.berkeley.edu/ftp/global/pub/speech/papers/eurospeech2005-mlp-cts.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.8297","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.8297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.sri.com/papers/eurospeech2005-mlp-cts.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W197151588","https://openalex.org/W336107121","https://openalex.org/W2090861223","https://openalex.org/W2094971681","https://openalex.org/W2106232466","https://openalex.org/W2134900903","https://openalex.org/W2142694085","https://openalex.org/W2150907703","https://openalex.org/W2165712214","https://openalex.org/W2167763959"],"related_works":["https://openalex.org/W2076543106","https://openalex.org/W2523437662","https://openalex.org/W89844371","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W4286643620","https://openalex.org/W4387048144","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2131711534"],"abstract_inverted_index":{"We":[0],"describe":[1],"the":[2,45,58,77],"development":[3],"of":[4,88,98,105],"a":[5,67,86,106,127,137],"speech":[6,12],"recognition":[7,109],"system":[8,110,124,140],"for":[9,91,118],"conversational":[10],"telephone":[11],"(CTS)":[13],"that":[14,141],"incorporates":[15],"acoustic":[16,24],"features":[17,25,65,117],"estimated":[18],"by":[19,34,74],"multilayer":[20],"perceptrons":[21],"(MLP).":[22],"The":[23,122],"are":[26,111],"based":[27,41,47],"on":[28,42,48,57,95],"frame-level":[29],"phone":[30],"posterior":[31],"probabilities,":[32],"obtained":[33,125],"merging":[35],"two":[36],"different":[37],"MLP":[38,116,146],"estimators,":[39],"one":[40],"PLP-Tandem":[43],"features,":[44],"other":[46],"hidden":[49],"activation":[50],"TRAPs":[51],"(HATs)":[52],"features.":[53,147],"This":[54],"paper":[55],"focuses":[56],"challenges":[59],"arising":[60],"when":[61],"incorporating":[62],"these":[63],"nonstandard":[64],"into":[66],"full-scale":[68],"speech-to-text":[69],"(STT)":[70],"system,":[71],"as":[72],"used":[73],"SRI":[75],"in":[76],"Fall":[78],"2004":[79],"DARPA":[80],"STT":[81],"evaluations.":[82],"First,":[83],"we":[84,101],"developed":[85],"series":[87],"time-saving":[89],"techniques":[90],"training":[92],"feature":[93],"MLPs":[94],"1800":[96],"hours":[97],"speech.":[99],"Second,":[100],"investigated":[102],"which":[103],"components":[104],"multipass,":[107],"multi-front-end":[108],"most":[112],"profitably":[113],"augmented":[114],"with":[115],"best":[119],"overall":[120],"performance.":[121],"final":[123],"achieved":[126],"2":[128],"%":[129,132],"absolute":[130],"(10":[131],"relative)":[133],"WER":[134],"reduction":[135],"over":[136],"comparable":[138],"baseline":[139],"did":[142],"not":[143],"include":[144],"Tandem/HATs":[145],"1.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}