{"id":"https://openalex.org/W1489048302","doi":"https://doi.org/10.1109/icassp.2015.7178830","title":"Learning feature mapping using deep neural network bottleneck features for distant large vocabulary speech recognition","display_name":"Learning feature mapping using deep neural network bottleneck features for distant large vocabulary speech recognition","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1489048302","doi":"https://doi.org/10.1109/icassp.2015.7178830","mag":"1489048302"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/record/207946/files/Himawan_ICASSP2015_2015.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039529498","display_name":"Ivan Himawan","orcid":"https://orcid.org/0000-0003-3848-244X"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ivan Himawan","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037750159","display_name":"David Imseng","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"David Imseng","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052265530","display_name":"Blaise Potard","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Blaise Potard","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100615740","display_name":"Namhoon Kim","orcid":"https://orcid.org/0000-0001-8504-4245"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Namhoon Kim","raw_affiliation_strings":["Samsung Electronics Co. Ltd., Suwon, South Korea","Samsung Electronics Co., Ltd , Suwon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co. Ltd., Suwon, South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Electronics Co., Ltd , Suwon, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100329194","display_name":"Jaewon Lee","orcid":"https://orcid.org/0000-0002-0768-384X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewon Lee","raw_affiliation_strings":["Samsung Electronics Co. Ltd., Suwon, South Korea","Samsung Electronics Co., Ltd , Suwon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co. Ltd., Suwon, South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Electronics Co., Ltd , Suwon, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2819,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93484766,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4540","last_page":"4544"},"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":0.9998000264167786,"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":0.9980000257492065,"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/speech-recognition","display_name":"Speech recognition","score":0.7899734377861023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7799156904220581},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7795112133026123},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7427210807800293},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5891490578651428},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5810707211494446},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5757195949554443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5224888920783997},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5193822979927063},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4943974018096924},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.45934659242630005},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.447734534740448},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4216313660144806},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09535270929336548}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7899734377861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7799156904220581},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7795112133026123},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7427210807800293},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5891490578651428},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5810707211494446},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5757195949554443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5224888920783997},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5193822979927063},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4943974018096924},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.45934659242630005},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.447734534740448},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4216313660144806},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09535270929336548},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2015.7178830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:207946","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/207946","pdf_url":"https://infoscience.epfl.ch/record/207946/files/Himawan_ICASSP2015_2015.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.864.3966","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.864.3966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/207946/files/Himawan_ICASSP2015_2015.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:207946","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/207946","pdf_url":"https://infoscience.epfl.ch/record/207946/files/Himawan_ICASSP2015_2015.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1489048302.pdf","grobid_xml":"https://content.openalex.org/works/W1489048302.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1524333225","https://openalex.org/W1537275613","https://openalex.org/W1964143424","https://openalex.org/W1973669708","https://openalex.org/W1985261152","https://openalex.org/W1985368711","https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2050091530","https://openalex.org/W2062164080","https://openalex.org/W2077541282","https://openalex.org/W2119203697","https://openalex.org/W2123237149","https://openalex.org/W2144786298","https://openalex.org/W2146871184","https://openalex.org/W2394967684","https://openalex.org/W2406395231","https://openalex.org/W2408713104","https://openalex.org/W2616139854","https://openalex.org/W6603403951","https://openalex.org/W6631362777","https://openalex.org/W6738021889"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2121652828","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,36,71,75],"recognition":[2,37],"from":[3,59],"distant":[4,35],"microphones":[5],"is":[6,43,93,113,124],"a":[7,49,118],"difficult":[8],"task":[9,38],"because":[10],"recordings":[11],"are":[12],"affected":[13],"by":[14],"reverberation":[15,54],"and":[16,55,73,90],"background":[17,56],"noise.":[18],"First,":[19],"the":[20,23,67,86,110],"application":[21],"of":[22,121],"deep":[24],"neural":[25],"network":[26],"(DNN)/hidden":[27],"Markov":[28],"model":[29],"(HMM)":[30],"hybrid":[31],"acoustic":[32],"models":[33],"for":[34,52],"using":[39,62],"AMI":[40,81],"meeting":[41,82],"corpus":[42,83],"investigated.":[44],"This":[45],"paper":[46],"then":[47],"proposes":[48],"feature":[50,111],"transformation":[51],"removing":[53],"noise":[57],"artefacts":[58],"bottleneck":[60,76,103],"features":[61,72],"DNN":[63],"trained":[64],"to":[65,115],"learn":[66],"mapping":[68,112],"between":[69,88],"distant-talking":[70,91],"close-talking":[74,89,107,116],"features.":[77],"Experimental":[78],"results":[79],"on":[80,106],"reveal":[84],"that":[85],"mismatch":[87],"conditions":[92],"largely":[94],"reduced,":[95],"with":[96],"about":[97],"16%":[98],"relative":[99,123],"improvement":[100],"over":[101],"conventional":[102],"system":[104],"(trained":[105],"speech).":[108],"If":[109],"applied":[114],"speech,":[117],"minor":[119],"degradation":[120],"4%":[122],"observed.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}
