{"id":"https://openalex.org/W2133338738","doi":"https://doi.org/10.1109/icassp.2005.1415282","title":"Automatically Transcribing Meetings using Distant Microphones","display_name":"Automatically Transcribing Meetings using Distant Microphones","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2133338738","doi":"https://doi.org/10.1109/icassp.2005.1415282","mag":"2133338738"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415282","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/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"F. Metze","raw_affiliation_strings":["Interactive Systems Laboratories, Universit\u00e4t Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, Universit\u00e4t Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048075735","display_name":"Christian F\u00fcgen","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"C. Fugen","raw_affiliation_strings":["Interactive Systems Laboratories, Universit\u00e4t Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, Universit\u00e4t Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108053345","display_name":"Yue Pan","orcid":"https://orcid.org/0000-0003-4572-8882"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Pan","raw_affiliation_strings":["Interactive Systems Laboratories, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Waibel","raw_affiliation_strings":["Interactive Systems Laboratories, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"989","last_page":"992"},"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":0.9998999834060669,"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":0.9990000128746033,"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/microphone","display_name":"Microphone","score":0.9065887331962585},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.88934326171875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7580884695053101},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6941661834716797},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5101607441902161},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4949943423271179},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.45805275440216064},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12855008244514465},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08282136917114258},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06010669469833374}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.9065887331962585},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.88934326171875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580884695053101},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6941661834716797},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5101607441902161},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4949943423271179},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.45805275440216064},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12855008244514465},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08282136917114258},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06010669469833374},{"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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2005.1415282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415282","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:10.1.1.60.8089","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.8089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isl.ira.uka.de/~fuegen/publications/metze_ICASSP_2005.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W76901566","https://openalex.org/W1554873843","https://openalex.org/W2002342963","https://openalex.org/W2106554350","https://openalex.org/W2121017435","https://openalex.org/W2150384167","https://openalex.org/W2153474519","https://openalex.org/W2405439032","https://openalex.org/W2594610113","https://openalex.org/W2915347754","https://openalex.org/W6603097216","https://openalex.org/W6713148914","https://openalex.org/W6931439903"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W2102249898","https://openalex.org/W2046724649","https://openalex.org/W2555586164","https://openalex.org/W4230838604","https://openalex.org/W2463186356"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"describe":[4],"our":[5,65],"efforts":[6],"to":[7,21,56],"develop":[8],"acoustic":[9],"models":[10],"suitable":[11],"for":[12,99,105],"distant":[13,36,52,100],"microphone":[14,37,92],"automatic":[15],"speech":[16,74,109,113],"recognition.":[17],"Our":[18],"goal":[19],"is":[20],"investigate":[22],"how":[23],"the":[24,48],"performance":[25,102],"of":[26,33,50,85,107],"a":[27,31,82],"system":[28,66],"trained":[29],"on":[30],"combination":[32],"close-talking":[34],"and":[35,59,103],"data":[38,75],"can":[39],"be":[40],"optimized,":[41],"while":[42],"assuming":[43],"as":[44,54],"little":[45],"information":[46],"about":[47],"configuration":[49],"(multiple)":[51],"microphones":[53,95],"possible,":[55],"avoid":[57],"guesstimates":[58],"lengthy":[60],"calibration":[61],"runs.":[62],"We":[63],"evaluated":[64],"in":[67],"NIST's":[68],"RT-04S":[69],"\"Meeting\"":[70],"speech-to-text":[71],"evaluation,":[72],"where":[73],"was":[76],"recorded":[77],"at":[78],"several":[79],"sites":[80],"with":[81,91,110],"varying":[83],"number":[84],"different":[86],"table-top":[87],"microphones,":[88],"but":[89],"not":[90],"arrays.":[93],"Body-mounted":[94],"provide":[96],"baseline":[97],"numbers":[98],"ASR":[101],"allow":[104],"comparisons":[106],"meeting":[108],"other":[111],"spontaneous":[112],"data.":[114]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
