{"id":"https://openalex.org/W2159344129","doi":"https://doi.org/10.1109/icassp.2005.1415159","title":"Automatic Processing of Audio Lectures for Information Retrieval: Vocabulary Selection and Language Modeling","display_name":"Automatic Processing of Audio Lectures for Information Retrieval: Vocabulary Selection and Language Modeling","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2159344129","doi":"https://doi.org/10.1109/icassp.2005.1415159","mag":"2159344129"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5064632326","display_name":"A. Park","orcid":null},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Park","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114018312","display_name":"Timothy J. Hazen","orcid":"https://orcid.org/0009-0006-1413-9590"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T.J. Hazen","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.R. Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405258931"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"497","last_page":"500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9955000281333923,"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":0.8842127919197083},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6958444714546204},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6698374152183533},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5986719727516174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5797238945960999},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5774639248847961},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5721114873886108},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5613155364990234},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5379493832588196},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4587441384792328},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.4489804208278656},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42886632680892944},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3990006744861603},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3879552483558655},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3669113516807556},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09885174036026001}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8842127919197083},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6958444714546204},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6698374152183533},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5986719727516174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5797238945960999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5774639248847961},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5721114873886108},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5613155364990234},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5379493832588196},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4587441384792328},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4489804208278656},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42886632680892944},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3990006744861603},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3879552483558655},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3669113516807556},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09885174036026001},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2005.1415159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.152.6975","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.152.6975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sls.lcs.mit.edu/sls/publications/2005/park-mit.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.377.7597","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.377.7597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.csail.mit.edu/hazen/publications/ICASSP05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W61448146","https://openalex.org/W2035451234","https://openalex.org/W2054293315","https://openalex.org/W2086891622","https://openalex.org/W2105079665","https://openalex.org/W2107755572","https://openalex.org/W2111732304","https://openalex.org/W2127914268","https://openalex.org/W2159748844","https://openalex.org/W6602583332"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W4385611764","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3],"initial":[4],"progress":[5],"towards":[6],"developing":[7],"a":[8,107],"system":[9],"for":[10,18,38],"automatically":[11],"transcribing":[12],"and":[13],"indexing":[14],"audio-visual":[15],"academic":[16],"lectures":[17],"audio":[19,50],"information":[20,51],"retrieval.":[21],"We":[22],"investigate":[23],"the":[24,90],"problem":[25],"of":[26,92],"how":[27],"to":[28,44,54,96],"combine":[29],"generic":[30],"spoken":[31],"data":[32,95],"sources":[33,37],"with":[34,78],"subject-specific":[35,97],"text":[36],"processing":[39],"lecture":[40],"speech.":[41],"In":[42],"addition":[43,91],"word":[45],"recognition":[46,80],"experiments,":[47],"we":[48,68,87],"perform":[49],"retrieval":[52,56,72,111],"simulations":[53],"characterize":[55],"performance":[57,73],"when":[58],"using":[59],"errorful":[60],"automatic":[61],"transcriptions.":[62],"Given":[63],"an":[64],"appropriately":[65],"selected":[66],"vocabulary,":[67],"observe":[69,88],"that":[70,89],"good":[71],"can":[74],"be":[75],"obtained":[76],"even":[77],"high":[79],"error":[81],"rates.":[82],"For":[83],"language":[84],"model":[85],"training,":[86],"spontaneous":[93],"speech":[94],"written":[98],"material":[99],"results":[100],"in":[101],"more":[102],"accurate":[103],"transcriptions,":[104],"but":[105],"has":[106],"marginal":[108],"effect":[109],"on":[110],"performance.":[112],"1.":[113]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
