{"id":"https://openalex.org/W2103933358","doi":"https://doi.org/10.1109/icassp.2009.4960579","title":"Unsupervised acoustic and language model training with small amounts of labelled data","display_name":"Unsupervised acoustic and language model training with small amounts of labelled data","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2103933358","doi":"https://doi.org/10.1109/icassp.2009.4960579","mag":"2103933358"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5027264910","display_name":"Scott Novotney","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Scott Novotney","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technologies, Cambridge, MA 02138, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technologies, Cambridge, MA 02138, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089653752","display_name":"Richard Schwartz","orcid":"https://orcid.org/0000-0002-4654-624X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard Schwartz","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technologies, Cambridge, MA 02138, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technologies, Cambridge, MA 02138, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111622458","display_name":"Jeff Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeff Ma","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technologies, Cambridge, MA 02138, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technologies, Cambridge, MA 02138, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027264910"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6041,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.93147386,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4297","last_page":"4300"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.7245507836341858},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7168242931365967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6322919130325317},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6253440380096436},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5710914134979248},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5178861618041992},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.494690865278244},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46710458397865295},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4553248882293701},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4450673758983612},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.427114337682724},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4264037013053894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16061952710151672},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1442912518978119},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14328891038894653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245507836341858},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7168242931365967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6322919130325317},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6253440380096436},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5710914134979248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5178861618041992},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.494690865278244},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46710458397865295},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4553248882293701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4450673758983612},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.427114337682724},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4264037013053894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16061952710151672},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1442912518978119},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14328891038894653},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.834.1766","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.834.1766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://clsp.jhu.edu/people/snovotne/papers/novotney_icassp09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W82886505","https://openalex.org/W160722039","https://openalex.org/W1975113979","https://openalex.org/W2066243589","https://openalex.org/W2094971681","https://openalex.org/W2110073835"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361","https://openalex.org/W2163537793","https://openalex.org/W2781555308","https://openalex.org/W4386794561","https://openalex.org/W2916997151","https://openalex.org/W3021690593","https://openalex.org/W2125343999"],"abstract_inverted_index":{"We":[0],"measure":[1],"the":[2,26,62,75,85,93],"effects":[3],"of":[4,16,29,46,51,61],"a":[5,81,108],"weak":[6],"language":[7,39,71,95],"model,":[8],"estimated":[9],"from":[10],"as":[11,13],"little":[12],"100k":[14,44],"words":[15,45],"text,":[17],"on":[18],"unsupervised":[19,38,54],"acoustic":[20,55],"model":[21,40,72,96],"training":[22,52],"and":[23,48,97],"then":[24],"explore":[25],"best":[27,86],"method":[28],"using":[30,101],"word":[31,76],"confidences":[32,77],"to":[33,67,79,120],"estimate":[34],"n-gram":[35],"counts":[36],"for":[37],"training.":[41,69],"Even":[42],"with":[43,59],"text":[47],"10":[49],"hours":[50],"data,":[53],"modeling":[56],"is":[57,111],"robust,":[58],"50%":[60],"gain":[63,110],"recovered":[64],"when":[65],"compared":[66],"supervised":[68],"For":[70],"training,":[73],"multiplying":[74],"together":[78],"get":[80],"weighted":[82],"count":[83],"produces":[84],"reduction":[87],"in":[88],"WER":[89],"by":[90],"2%":[91],"over":[92,100],"baseline":[94],"0.5%":[98],"absolute":[99],"unweighted":[102],"transcripts.":[103],"Oracle":[104],"experiments":[105],"show":[106],"that":[107],"larger":[109],"possible,":[112],"but":[113],"better":[114],"confidence":[115],"estimation":[116],"techniques":[117],"are":[118],"needed":[119],"identify":[121],"correct":[122],"n-grams.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}