{"id":"https://openalex.org/W1754457604","doi":"https://doi.org/10.1109/icassp.2015.7178798","title":"Spatial diffuseness features for DNN-based speech recognition in noisy and reverberant environments","display_name":"Spatial diffuseness features for DNN-based speech recognition in noisy and reverberant environments","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1754457604","doi":"https://doi.org/10.1109/icassp.2015.7178798","mag":"1754457604"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178798","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1410.2479","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015722753","display_name":"Andreas Schwarz","orcid":"https://orcid.org/0000-0001-5484-3976"},"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":"Andreas Schwarz","raw_affiliation_strings":["Multimedia Communications and Signal Processing Friedrich-Alexander-Universitat Erlangen - Nurnberg (FAU), Germany","Multimedia Communications and Signal Processing, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Cauerstr. 7, 91058, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing Friedrich-Alexander-Universitat Erlangen - Nurnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Multimedia Communications and Signal Processing, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Cauerstr. 7, 91058, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039041764","display_name":"Christian Huemmer","orcid":"https://orcid.org/0000-0002-4341-4217"},"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":"Christian Huemmer","raw_affiliation_strings":["Multimedia Communications and Signal Processing Friedrich-Alexander-Universitat Erlangen - Nurnberg (FAU), Germany","Multimedia Communications and Signal Processing, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Cauerstr. 7, 91058, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing Friedrich-Alexander-Universitat Erlangen - Nurnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Multimedia Communications and Signal Processing, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Cauerstr. 7, 91058, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090454997","display_name":"Roland Maas","orcid":null},"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":"Roland Maas","raw_affiliation_strings":["Friedrich-Alexander-Universitat Erlangen-Nurnberg, Erlangen, Bayern, DE","Multimedia Communications and Signal Processing, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Cauerstr. 7, 91058, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universitat Erlangen-Nurnberg, Erlangen, Bayern, DE","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Multimedia Communications and Signal Processing, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Cauerstr. 7, 91058, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"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 Friedrich-Alexander-Universitat Erlangen - Nurnberg (FAU), Germany","Multimedia Communications and Signal Processing, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Cauerstr. 7, 91058, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing Friedrich-Alexander-Universitat Erlangen - Nurnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Multimedia Communications and Signal Processing, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Cauerstr. 7, 91058, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":5.1,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.96751468,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":null,"first_page":"4380","last_page":"4384"},"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":0.9995999932289124,"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":0.9988999962806702,"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":0.7814575433731079},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6750491261482239},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6423963308334351},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6197500228881836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5873351097106934},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5089111328125},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.497816801071167},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48214003443717957},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4696354568004608},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44269296526908875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814575433731079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6750491261482239},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6423963308334351},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6197500228881836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5873351097106934},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5089111328125},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.497816801071167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48214003443717957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4696354568004608},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44269296526908875},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178798","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:arXiv.org:1410.2479","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1410.2479","pdf_url":"https://arxiv.org/pdf/1410.2479","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1410.2479","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1410.2479","pdf_url":"https://arxiv.org/pdf/1410.2479","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W626929012","https://openalex.org/W1524333225","https://openalex.org/W1969838670","https://openalex.org/W1984541135","https://openalex.org/W1985368711","https://openalex.org/W1989314204","https://openalex.org/W2026369565","https://openalex.org/W2028742541","https://openalex.org/W2038730156","https://openalex.org/W2042141988","https://openalex.org/W2044617339","https://openalex.org/W2048526402","https://openalex.org/W2061835742","https://openalex.org/W2062164080","https://openalex.org/W2135340340","https://openalex.org/W2160815625","https://openalex.org/W2166547995","https://openalex.org/W2184045248","https://openalex.org/W2295119550","https://openalex.org/W2394967684","https://openalex.org/W2616139854","https://openalex.org/W2762693443","https://openalex.org/W3124056356","https://openalex.org/W4285719527","https://openalex.org/W4313371711","https://openalex.org/W6631362777","https://openalex.org/W6646783955","https://openalex.org/W6697090674","https://openalex.org/W6711908631","https://openalex.org/W6745258804"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W2547793174","https://openalex.org/W2132885390","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,70,76],"spatial":[3],"diffuseness":[4,63],"feature":[5,24,64],"for":[6,81],"deep":[7],"neural":[8],"network":[9],"(DNN)-based":[10],"automatic":[11],"speech":[12],"recognition":[13,16],"to":[14,69,75,88],"improve":[15],"accuracy":[17],"in":[18,27,51],"reverberant":[19],"and":[20,43,54,95],"noisy":[21,93],"environments.":[22],"The":[23],"is":[25,58],"computed":[26],"real-time":[28],"from":[29,92],"multiple":[30],"microphone":[31],"signals":[32],"without":[33],"requiring":[34],"knowledge":[35],"or":[36],"estimation":[37],"of":[38,41,48],"the":[39,45,62,82],"direction":[40],"arrival,":[42],"represents":[44],"relative":[46],"amount":[47],"diffuse":[49],"noise":[50],"each":[52],"time":[53],"frequency":[55],"bin.":[56],"It":[57],"shown":[59],"that":[60],"using":[61],"as":[65],"an":[66],"additional":[67],"input":[68],"DNN-based":[71],"acoustic":[72],"model":[73],"leads":[74],"reduced":[77],"word":[78],"error":[79],"rate":[80],"REVERB":[83],"challenge":[84],"corpus,":[85],"both":[86],"compared":[87],"logmelspec":[89],"features":[90,96],"extracted":[91],"signals,":[94],"enhanced":[97],"by":[98],"spectral":[99],"subtraction.":[100]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2016-06-24T00:00:00"}