{"id":"https://openalex.org/W2116361377","doi":"https://doi.org/10.1109/tasl.2010.2040782","title":"Hierarchical Bayesian Language Models for Conversational Speech Recognition","display_name":"Hierarchical Bayesian Language Models for Conversational Speech Recognition","publication_year":2010,"publication_date":"2010-01-22","ids":{"openalex":"https://openalex.org/W2116361377","doi":"https://doi.org/10.1109/tasl.2010.2040782","mag":"2116361377"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2040782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2040782","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://era.ed.ac.uk/bitstream/1842/4528/1/huang-taslp10.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047856952","display_name":"Songfang Huang","orcid":"https://orcid.org/0000-0001-8084-0904"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Songfang Huang","raw_affiliation_strings":["Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"S Renals","raw_affiliation_strings":["Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":4.592,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.9471921,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"18","issue":"8","first_page":"1941","last_page":"1954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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":0.9965000152587891,"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/perplexity","display_name":"Perplexity","score":0.8505765199661255},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7773264646530151},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7214975953102112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5911800861358643},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.573832094669342},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5496358871459961},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4813997745513916},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4530961811542511},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.44595834612846375},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4313053488731384},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.41926664113998413},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3984960615634918},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18028584122657776},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08919870853424072}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8505765199661255},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773264646530151},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7214975953102112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5911800861358643},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.573832094669342},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5496358871459961},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4813997745513916},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4530961811542511},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44595834612846375},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4313053488731384},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.41926664113998413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3984960615634918},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18028584122657776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08919870853424072},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2010.2040782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2040782","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/4528","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/4528","pdf_url":"https://era.ed.ac.uk/bitstream/1842/4528/1/huang-taslp10.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.208.7450","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.208.7450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2010/huang-taslp10.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/4528","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/4528","pdf_url":"https://era.ed.ac.uk/bitstream/1842/4528/1/huang-taslp10.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2116361377.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W10097614","https://openalex.org/W160901726","https://openalex.org/W263845233","https://openalex.org/W1424447973","https://openalex.org/W1508165687","https://openalex.org/W1516111018","https://openalex.org/W1526361935","https://openalex.org/W1542491098","https://openalex.org/W1579838312","https://openalex.org/W1597533204","https://openalex.org/W1631260214","https://openalex.org/W1934041838","https://openalex.org/W1967687583","https://openalex.org/W2005902041","https://openalex.org/W2007553631","https://openalex.org/W2015093644","https://openalex.org/W2027499299","https://openalex.org/W2045656233","https://openalex.org/W2053218206","https://openalex.org/W2056250865","https://openalex.org/W2069429561","https://openalex.org/W2075201173","https://openalex.org/W2082092506","https://openalex.org/W2083751884","https://openalex.org/W2087309226","https://openalex.org/W2103731025","https://openalex.org/W2111305191","https://openalex.org/W2121227244","https://openalex.org/W2122560783","https://openalex.org/W2132339004","https://openalex.org/W2132957691","https://openalex.org/W2134237567","https://openalex.org/W2134963415","https://openalex.org/W2135194391","https://openalex.org/W2143707047","https://openalex.org/W2151967501","https://openalex.org/W2153773386","https://openalex.org/W2154099718","https://openalex.org/W2156833271","https://openalex.org/W2158195707","https://openalex.org/W2159399018","https://openalex.org/W2159782014","https://openalex.org/W2467379829","https://openalex.org/W3141933106","https://openalex.org/W4232383088","https://openalex.org/W4233559841","https://openalex.org/W4285719527","https://openalex.org/W6600402650","https://openalex.org/W6628438334","https://openalex.org/W6635726886","https://openalex.org/W6664420536","https://openalex.org/W6675752074","https://openalex.org/W6682569104","https://openalex.org/W6683650587"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2050138804","https://openalex.org/W2151348424","https://openalex.org/W1494910745"],"abstract_inverted_index":{"Traditional":[0],"<formula":[1],"formulatype=\"inline\"":[2],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[3],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex":[4],"Notation=\"TeX\">$n$</tex>":[5],"</formula>":[6],"-gram":[7],"language":[8,51,67,93],"models":[9],"are":[10,96],"widely":[11],"used":[12],"in":[13,84,102],"state-of-the-art":[14],"large":[15],"vocabulary":[16],"speech":[17,83],"recognition":[18,80],"systems.":[19],"This":[20,61],"simple":[21],"model":[22,68],"suffers":[23],"from":[24],"some":[25],"limitations,":[26],"such":[27],"as":[28],"overfitting":[29],"of":[30,36,81],"maximum-likelihood":[31],"estimation":[32],"and":[33,104],"the":[34,71,79],"lack":[35],"rich":[37],"contextual":[38],"knowledge":[39],"sources.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,95],"exploit":[45],"a":[46,55,63],"hierarchical":[47,91],"Bayesian":[48,92],"interpretation":[49],"for":[50,74],"modeling,":[52],"based":[53],"on":[54,78],"nonparametric":[56],"prior":[57],"called":[58],"Pitman\u2013Yor":[59],"process.":[60],"offers":[62],"principled":[64],"approach":[65],"to":[66,98],"smoothing,":[69],"embedding":[70],"power-law":[72],"distribution":[73],"natural":[75],"language.":[76],"Experiments":[77],"conversational":[82],"multiparty":[85],"meetings":[86],"demonstrate":[87],"that":[88],"by":[89],"using":[90],"models,":[94],"able":[97],"achieve":[99],"significant":[100],"reductions":[101],"perplexity":[103],"word":[105],"error":[106],"rate.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
