{"id":"https://openalex.org/W2291768582","doi":"https://doi.org/10.1109/asru.2015.7404832","title":"A CHiME-3 challenge system: Long-term acoustic features for noise robust automatic speech recognition","display_name":"A CHiME-3 challenge system: Long-term acoustic features for noise robust automatic speech recognition","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2291768582","doi":"https://doi.org/10.1109/asru.2015.7404832","mag":"2291768582"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5071286568","display_name":"Niko Moritz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Niko Moritz","raw_affiliation_strings":["Fraunhofer IDMT, Project Group for Hearing, Speech, and Audio Technology, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Project Group for Hearing, Speech, and Audio Technology, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051972559","display_name":"Stephan Gerlach","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stephan Gerlach","raw_affiliation_strings":["Fraunhofer IDMT, Project Group for Hearing, Speech, and Audio Technology, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Project Group for Hearing, Speech, and Audio Technology, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010480213","display_name":"Kamil Adilo\u011flu","orcid":"https://orcid.org/0000-0003-0172-8485"},"institutions":[{"id":"https://openalex.org/I4210108766","display_name":"Klinikum Oldenburg","ror":"https://ror.org/01t0n2c80","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210108766"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kamil Adiloglu","raw_affiliation_strings":["Hortech gGmbH, Oldenburg, Germany","Cluster of Excellence Hearing4All, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Hortech gGmbH, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210108766"]},{"raw_affiliation_string":"Cluster of Excellence Hearing4All, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001993329","display_name":"Jorn Anemulle","orcid":null},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorn Anemulle","raw_affiliation_strings":["University of Oldenburg, Medical Physics Department, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Oldenburg, Medical Physics Department, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076869895","display_name":"Birger Kollmeier","orcid":"https://orcid.org/0000-0001-8584-4779"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Birger Kollmeier","raw_affiliation_strings":["Fraunhofer IDMT, Project Group for Hearing, Speech, and Audio Technology, Oldenburg, Germany","Medical Physics Department, University of Oldenburg, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Project Group for Hearing, Speech, and Audio Technology, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210138578"]},{"raw_affiliation_string":"Medical Physics Department, University of Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027797344","display_name":"Stefan Goetze","orcid":"https://orcid.org/0000-0003-1044-7343"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Goetze","raw_affiliation_strings":["Fraunhofer IDMT, Project Group for Hearing, Speech, and Audio Technology, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Project Group for Hearing, Speech, and Audio Technology, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210138578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5071286568"],"corresponding_institution_ids":["https://openalex.org/I4210138578"],"apc_list":null,"apc_paid":null,"fwci":1.7464,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85687942,"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":"468","last_page":"474"},"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.8121285438537598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.750937819480896},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6853833794593811},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.6028765439987183},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5280236601829529},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4904162585735321},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4667537212371826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4363267123699188},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4148254692554474},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3895696699619293},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3812634348869324},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37045782804489136},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1178518533706665},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.09815481305122375}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8121285438537598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750937819480896},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6853833794593811},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6028765439987183},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5280236601829529},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4904162585735321},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4667537212371826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4363267123699188},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4148254692554474},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3895696699619293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3812634348869324},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37045782804489136},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1178518533706665},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.09815481305122375},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2015.7404832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/393881","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/393881","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W95870201","https://openalex.org/W1509088290","https://openalex.org/W1524333225","https://openalex.org/W1542280630","https://openalex.org/W1555217905","https://openalex.org/W1910234244","https://openalex.org/W1974932989","https://openalex.org/W1993882792","https://openalex.org/W2002342963","https://openalex.org/W2024490156","https://openalex.org/W2048488652","https://openalex.org/W2063689849","https://openalex.org/W2076502758","https://openalex.org/W2103387126","https://openalex.org/W2113638573","https://openalex.org/W2126048084","https://openalex.org/W2131342762","https://openalex.org/W2136922672","https://openalex.org/W2149693148","https://openalex.org/W2150907703","https://openalex.org/W2159373586","https://openalex.org/W2160815625","https://openalex.org/W2289394825","https://openalex.org/W2408093180","https://openalex.org/W3105118415","https://openalex.org/W6603838363","https://openalex.org/W6630309668","https://openalex.org/W6631362777","https://openalex.org/W6682398751"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2401089611","https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W2114026179","https://openalex.org/W2089240210","https://openalex.org/W4200596008"],"abstract_inverted_index":{"The":[0,22,53],"paper":[1],"describes":[2],"an":[3,162],"automatic":[4],"speech":[5,28,47,121],"recognition":[6],"(ASR)":[7],"system":[8,24,178],"for":[9],"the":[10,43,57,60,63,99,174,180],"3rd":[11],"CHiME":[12],"challenge":[13,115],"that":[14,38,95],"addresses":[15],"noisy":[16],"acoustic":[17,75,156],"scenes":[18],"within":[19],"public":[20],"environments.":[21],"proposed":[23],"includes":[25,153],"a":[26,32,70,79,111,136,145],"multi-channel":[27],"enhancement":[29],"front-end":[30],"including":[31],"microphone":[33,51],"channel":[34],"failure":[35],"detection":[36],"method":[37,71,138],"is":[39,59,93,128],"based":[40,89,139],"on":[41,110,140,179],"cross-comparing":[42],"modulation":[44,65],"spectra":[45],"of":[46,56,62,105,120,155,168],"to":[48,72,78,130,135,158,173],"detect":[49],"erroneous":[50],"recordings.":[52],"main":[54],"focus":[55],"submission":[58],"investigation":[61],"amplitude":[64],"filter":[66,106],"bank":[67,107],"(AMFB)":[68],"as":[69],"extract":[73],"long-term":[74],"cues":[76],"prior":[77],"Gaussian":[80],"mixture":[81],"model":[82],"(GMM)":[83],"or":[84],"deep":[85],"neural":[86],"network":[87],"(DNN)":[88],"ASR":[90,114,149],"classifier.":[91],"It":[92],"shown":[94,129],"AMFB":[96],"features":[97,108,157],"outperform":[98],"commonly":[100],"used":[101],"frame":[102],"splicing":[103],"technique":[104],"even":[109],"performance":[112],"optimized":[113],"system.":[116],"I.e.,":[117],"temporal":[118,142],"analysis":[119],"by":[122],"hand-crafted":[123],"and":[124],"auditory":[125],"motivated":[126],"AMFBs":[127],"be":[131],"more":[132],"robust":[133],"compared":[134],"data-driven":[137],"extracting":[141],"dynamics":[143],"with":[144],"DNN.":[146],"Our":[147],"final":[148],"system,":[150],"which":[151],"additionally":[152],"adaptation":[154],"speaker":[159],"characteristics,":[160],"achieves":[161],"absolute":[163],"word":[164],"error":[165],"rate":[166],"reduction":[167],"approx.":[169],"21.53":[170],"%":[171],"relative":[172],"best":[175],"CHiME-3":[176],"baseline":[177],"\"real\"":[181],"test":[182],"condition.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}