{"id":"https://openalex.org/W2177365772","doi":"https://doi.org/10.21437/interspeech.2015-248","title":"Channel selection in the short-time modulation domain for distant speech recognition","display_name":"Channel selection in the short-time modulation domain for distant speech recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2177365772","doi":"https://doi.org/10.21437/interspeech.2015-248","mag":"2177365772"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-248","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/record/209075/files/Himawan_INTERSPEECH_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":true,"raw_author_name":"Ivan Himawan","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, 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"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Science and Engineering Faculty, Queensland University of Technology"],"affiliations":[{"raw_affiliation_string":"Science and Engineering Faculty, Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000014182","display_name":"David Dean","orcid":"https://orcid.org/0000-0003-1274-9775"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Dean","raw_affiliation_strings":["Science and Engineering Faculty, Queensland University of Technology"],"affiliations":[{"raw_affiliation_string":"Science and Engineering Faculty, Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053074581","display_name":"Dian Tjondronegoro","orcid":"https://orcid.org/0000-0001-7446-2839"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dian Tjondronegoro","raw_affiliation_strings":["Science and Engineering Faculty, Queensland University of Technology"],"affiliations":[{"raw_affiliation_string":"Science and Engineering Faculty, Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039529498"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.1579,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79286085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"741","last_page":"745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9987000226974487,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7712339758872986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7509913444519043},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7446273565292358},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6763921976089478},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6385564804077148},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5431368350982666},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5429051518440247},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5292508006095886},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5083751082420349},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4617356061935425},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.42924830317497253},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.4182504117488861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3145279884338379},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2209034562110901},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17232003808021545},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16090649366378784},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.07217967510223389}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7712339758872986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509913444519043},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7446273565292358},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6763921976089478},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6385564804077148},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5431368350982666},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5429051518440247},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5292508006095886},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5083751082420349},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4617356061935425},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.42924830317497253},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.4182504117488861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3145279884338379},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2209034562110901},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17232003808021545},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16090649366378784},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.07217967510223389},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-248","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:209075","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/115240","pdf_url":"https://infoscience.epfl.ch/record/209075/files/Himawan_INTERSPEECH_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":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:209075","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/115240","pdf_url":"https://infoscience.epfl.ch/record/209075/files/Himawan_INTERSPEECH_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":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2177365772.pdf","grobid_xml":"https://content.openalex.org/works/W2177365772.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1480055486","https://openalex.org/W1495679096","https://openalex.org/W1509052650","https://openalex.org/W1514905536","https://openalex.org/W1524333225","https://openalex.org/W1552282138","https://openalex.org/W1973669708","https://openalex.org/W1973787919","https://openalex.org/W1980759728","https://openalex.org/W2004405928","https://openalex.org/W2018887914","https://openalex.org/W2027227339","https://openalex.org/W2075012882","https://openalex.org/W2098434929","https://openalex.org/W2115515280","https://openalex.org/W2129227482","https://openalex.org/W2147166770","https://openalex.org/W2152037357","https://openalex.org/W2153485077","https://openalex.org/W2952350176","https://openalex.org/W4300582463"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4387473770"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,17,59,64,85],"recognition":[2,96],"from":[3,60,66],"multiple":[4],"distant":[5],"microphones":[6,22],"poses":[7],"significant":[8],"challenges":[9],"because":[10,23],"of":[11,16,24,26,58,81,84],"noise":[12],"and":[13,28,63,89,102],"reverberations.The":[14],"quality":[15,86],"acquisition":[18],"may":[19],"vary":[20],"between":[21],"movements":[25],"speakers":[27],"channel":[29,34,111],"distortions.This":[30],"paper":[31],"proposes":[32],"a":[33],"selection":[35,43],"approach":[36,53],"for":[37],"selecting":[38],"reliable":[39],"channels":[40],"based":[41],"on":[42],"criterion":[44],"operating":[45],"in":[46,74,79,95],"the":[47,55,75,107,110],"short-term":[48],"modulation":[49],"spectrum":[50],"domain.The":[51],"proposed":[52],"quantifies":[54],"relative":[56],"strength":[57],"each":[61],"microphone":[62,117],"obtained":[65],"beamforming":[67],"modulations.The":[68],"new":[69],"technique":[70],"is":[71,98,112],"compared":[72,105],"experimentally":[73],"real":[76],"reverb":[77],"conditions":[78],"terms":[80],"perceptual":[82],"evaluation":[83],"(PESQ)":[87],"measures":[88],"word":[90],"error":[91],"rate":[92,97],"(WER).Overall":[93],"improvement":[94],"observed":[99],"using":[100,115],"delay-sum":[101],"superdirective":[103],"beamformers":[104],"to":[106],"case":[108],"when":[109],"selected":[113],"randomly":[114],"circular":[116],"arrays.":[118]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
