{"id":"https://openalex.org/W2072856494","doi":"https://doi.org/10.1109/icassp.2002.5745595","title":"Experiments on distant-talking speech recognition in meeting room using extended MAM","display_name":"Experiments on distant-talking speech recognition in meeting room using extended MAM","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2072856494","doi":"https://doi.org/10.1109/icassp.2002.5745595","mag":"2072856494"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745595","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/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":["Carnegie Mellon University, United States","Carnegie-Mellon University (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University (United States)","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":"Alex Waibel","raw_affiliation_strings":["Carnegie Mellon University, United States","Carnegie-Mellon University (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University (United States)","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"IV","last_page":"4165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.9855999946594238,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.967199981212616,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-recognition","display_name":"Speech recognition","score":0.8302822113037109},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8190973997116089},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7366737127304077},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7134630084037781},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.43660444021224976},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.42492321133613586},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4160434603691101},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4131561815738678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40253937244415283},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33410996198654175}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8302822113037109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190973997116089},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7366737127304077},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7134630084037781},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.43660444021224976},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.42492321133613586},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4160434603691101},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4131561815738678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40253937244415283},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33410996198654175},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5745595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745595","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1573992054","https://openalex.org/W1599690842","https://openalex.org/W2753053412","https://openalex.org/W2665157442","https://openalex.org/W3108840034","https://openalex.org/W4388169484","https://openalex.org/W2363259562","https://openalex.org/W3036937347","https://openalex.org/W3149224203","https://openalex.org/W2401089611"],"abstract_inverted_index":{"MAM":[0,33,60,80],"has":[1],"been":[2],"successfully":[3],"used":[4],"to":[5,41,127],"improve":[6],"the":[7,18,51,55,59,67,73,133],"noise":[8,45],"robustness":[9],"of":[10,20,75,143],"speech":[11,22,77,102,106,149],"recognizers.":[12],"We":[13,111],"apply":[14],"this":[15],"method":[16,86],"in":[17,81,90],"exploration":[19],"distant-talking":[21,105,154],"recognition":[23,57,93],"for":[24,43,145,152],"meeting":[25,117],"room":[26],"system,":[27,58,119],"and":[28,38,46,70,103,150],"propose":[29],"a":[30,114],"new":[31],"extended":[32,131],"algorithm":[34],"combined":[35],"with":[36,54,66,83,120],"LDA":[37,52],"MLLR":[39,87],"techniques":[40],"compensate":[42],"additive":[44,100,147],"channel":[47],"variation.":[48],"By":[49,129],"sharing":[50],"matrix":[53],"core":[56],"secondary":[61],"model":[62,84],"is":[63],"coupled":[64],"better":[65],"intended":[68],"system":[69,135],"can":[71,88],"take":[72],"advantage":[74],"context":[76],"frames.":[78],"Using":[79],"conjunction":[82],"adaptation":[85],"result":[89],"further":[91],"improved":[92,134],"accuracy.":[94],"Our":[95],"database":[96],"includes":[97],"simulated":[98],"10dB":[99,146],"noisy":[101,148],"real":[104,153],"by":[107],"8-channel":[108],"simultaneous":[109],"recording.":[110],"started":[112],"from":[113,125],"baseline":[115],"LVCSR":[116],"transcription":[118],"word":[121],"error":[122,140],"rate":[123,141],"range":[124],"25":[126],"55%.":[128],"applying":[130],"MAM,":[132],"achieves":[136],"an":[137],"average":[138],"relative":[139],"reduction":[142],"27%":[144],"15%":[151],"speech.":[155]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}