{"id":"https://openalex.org/W2117459613","doi":"https://doi.org/10.1109/icassp.2012.6288904","title":"Investigations on exemplar-based features for speech recognition towards thousands of hours of unsupervised, noisy data","display_name":"Investigations on exemplar-based features for speech recognition towards thousands of hours of unsupervised, noisy data","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2117459613","doi":"https://doi.org/10.1109/icassp.2012.6288904","mag":"2117459613"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5071956319","display_name":"Georg Heigold","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Georg Heigold","raw_affiliation_strings":["Google, Inc., USA","Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111455517","display_name":"Patrick Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Nguyen","raw_affiliation_strings":["Google, Inc., USA","Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108513736","display_name":"M. Weintraub","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitchel Weintraub","raw_affiliation_strings":["Google, Inc., USA","Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013813527","display_name":"Vincent Vanhoucke","orcid":"https://orcid.org/0000-0003-0544-2791"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Vanhoucke","raw_affiliation_strings":["Google, Inc., USA","Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071956319"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":3.537,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93047998,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4437","last_page":"4440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.8381268978118896},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7405886650085449},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6391089558601379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.601697564125061},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5194689631462097},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4988889694213867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.478302538394928},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.46569761633872986},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.46410831809043884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3616899251937866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8381268978118896},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7405886650085449},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6391089558601379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.601697564125061},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5194689631462097},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4988889694213867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.478302538394928},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.46569761633872986},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.46410831809043884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3616899251937866},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.474","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/37825.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1592796124","https://openalex.org/W2069737407","https://openalex.org/W2072493763","https://openalex.org/W2095959744","https://openalex.org/W2097207027","https://openalex.org/W2118595744","https://openalex.org/W2131033001","https://openalex.org/W2131964822","https://openalex.org/W2144071798"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W2133032418"],"abstract_inverted_index":{"The":[0],"acoustic":[1,35],"models":[2],"in":[3,12,27,43],"state-of-the-art":[4],"speech":[5],"recognition":[6],"systems":[7],"are":[8,15,39,51,60,125],"based":[9],"on":[10,89,106],"phones":[11],"context":[13],"that":[14,28],"represented":[16],"by":[17],"hidden":[18],"Markov":[19],"models.":[20],"This":[21,64,97],"modeling":[22,109],"approach":[23,69,98],"may":[24],"be":[25],"limited":[26],"it":[29],"is":[30,82],"hard":[31],"to":[32,84],"incorporate":[33],"long-span":[34],"context.":[36],"Exemplar-based":[37],"approaches":[38],"an":[40,67],"attractive":[41],"alter-native,":[42],"particular":[44],"if":[45],"massive":[46],"data":[47,57,76],"and":[48,62,104,121],"computational":[49],"power":[50],"available.":[52],"Yet,":[53],"most":[54],"of":[55,110],"the":[56,86,90,94,107,118,122],"at":[58,100],"Google":[59],"unsupervised":[61],"noisy.":[63],"paper":[65],"investigates":[66],"exemplar-based":[68,87],"under":[70],"this":[71],"yet":[72],"not":[73],"well":[74],"understood":[75],"regime.":[77],"A":[78],"log-linear":[79],"rescoring":[80],"framework":[81],"used":[83],"combine":[85],"features":[88],"word":[91],"level":[92],"with":[93,112],"first-pass":[95],"model.":[96],"guarantees":[99],"least":[101],"baseline":[102],"performance":[103],"focuses":[105],"refined":[108],"words":[111],"sufficient":[113],"data.":[114],"Experimental":[115],"results":[116],"for":[117],"Voice":[119],"Search":[120],"YouTube":[123],"tasks":[124],"presented.":[126]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}