{"id":"https://openalex.org/W2703224471","doi":"https://doi.org/10.1109/icassp.2017.7953083","title":"Online environmental adaptation of CNN-based acoustic models using spatial diffuseness features","display_name":"Online environmental adaptation of CNN-based acoustic models using spatial diffuseness features","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2703224471","doi":"https://doi.org/10.1109/icassp.2017.7953083","mag":"2703224471"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5039041764","display_name":"Christian Huemmer","orcid":"https://orcid.org/0000-0002-4341-4217"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Christian Huemmer","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068787682","display_name":"Walter Kellermann","orcid":"https://orcid.org/0000-0002-6501-3174"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Walter Kellermann","raw_affiliation_strings":["Multimedia Communications and Signal Processing, FAU Erlangen-Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, FAU Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4875","last_page":"4879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.7388699054718018},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.675805926322937},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6183276772499084},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4532831311225891},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4528832733631134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4203878939151764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3608059287071228},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35437634587287903},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3531615138053894},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10848963260650635},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0946374237537384},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.08571383357048035},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07451274991035461},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05813434720039368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7388699054718018},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.675805926322937},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6183276772499084},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4532831311225891},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4528832733631134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4203878939151764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3608059287071228},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35437634587287903},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3531615138053894},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10848963260650635},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0946374237537384},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.08571383357048035},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07451274991035461},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05813434720039368},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1513820424","https://openalex.org/W1513862252","https://openalex.org/W1571447047","https://openalex.org/W1754457604","https://openalex.org/W1931312565","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2028742541","https://openalex.org/W2033310064","https://openalex.org/W2038730156","https://openalex.org/W2044617339","https://openalex.org/W2045317385","https://openalex.org/W2048526313","https://openalex.org/W2062164080","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2090320273","https://openalex.org/W2094147890","https://openalex.org/W2117239706","https://openalex.org/W2155648385","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2166547995","https://openalex.org/W2288645994","https://openalex.org/W2337992322","https://openalex.org/W2397761413","https://openalex.org/W2402922286","https://openalex.org/W2403445744","https://openalex.org/W2403731734","https://openalex.org/W2408583661","https://openalex.org/W2514021858","https://openalex.org/W2584063687","https://openalex.org/W3124056356","https://openalex.org/W6637567912","https://openalex.org/W6703705403","https://openalex.org/W6713273328","https://openalex.org/W6732766861"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2766405861","https://openalex.org/W2360975119","https://openalex.org/W2912421143","https://openalex.org/W2372487155"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"new":[3],"concept":[4],"for":[5,37,68],"adapting":[6],"CNN-based":[7,56],"acoustic":[8,19,52,57],"models":[9],"using":[10,94],"spatial":[11,22,95],"diffuseness":[12,23,96],"features":[13,24,31],"as":[14,28],"auxiliary":[15],"information":[16],"about":[17],"the":[18,21,69,74,82,90],"environment:":[20],"are":[25],"simultaneously":[26],"employed":[27],"acoustic-model":[29],"input":[30],"and":[32,64,102,111],"to":[33,49,100,104],"estimate":[34],"environmental":[35,62],"cues":[36],"context":[38],"adaptation,":[39],"where":[40],"one":[41],"convolutional":[42],"layer":[43],"is":[44,65],"factorized":[45],"into":[46],"several":[47],"sub-layers":[48],"represent":[50],"different":[51],"conditions.":[53],"This":[54],"context-adaptive":[55],"model":[58],"facilitates":[59],"an":[60],"online":[61],"adaptation":[63],"experimentally":[66],"verified":[67],"real-world":[70],"recordings":[71],"provided":[72],"by":[73,89],"CHiME-3":[75],"task.":[76],"The":[77],"best":[78],"performing":[79],"setup":[80],"reduces":[81],"average":[83],"word":[84],"error":[85],"rate":[86],"scores":[87],"achieved":[88],"baseline":[91],"system":[92],"(without":[93],"features)":[97],"from":[98],"19.4%":[99],"15.9%":[101],"12.2%":[103],"10.7%":[105],"considering":[106],"two":[107],"experimental":[108],"setups":[109],"with":[110],"without":[112],"front-end":[113],"signal":[114],"enhancement,":[115],"respectively.":[116]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}