{"id":"https://openalex.org/W2938737578","doi":"https://doi.org/10.1109/icassp.2019.8682991","title":"An Analysis of Noise-aware Features in Combination with the Size and Diversity of Training Data for DNN-based Speech Enhancement","display_name":"An Analysis of Noise-aware Features in Combination with the Size and Diversity of Training Data for DNN-based Speech Enhancement","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938737578","doi":"https://doi.org/10.1109/icassp.2019.8682991","mag":"2938737578"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5041108140","display_name":"Robert Rehr","orcid":"https://orcid.org/0000-0001-7458-2320"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Robert Rehr","raw_affiliation_strings":["Signal Processing Group, Department of Informatics, Universit\u00e4t Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Informatics, Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087022569","display_name":"Timo Gerkmann","orcid":"https://orcid.org/0000-0002-8678-4699"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Gerkmann","raw_affiliation_strings":["Signal Processing Group, Department of Informatics, Universit\u00e4t Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Informatics, Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041108140"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":0.9951,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75500184,"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":"601","last_page":"605"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7242395281791687},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6557389497756958},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.60914546251297},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5439578890800476},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4997069835662842},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4958532750606537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4941733181476593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4607032835483551},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44615015387535095},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44346413016319275},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43410515785217285},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4192134737968445},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3113276958465576},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15096250176429749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242395281791687},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6557389497756958},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.60914546251297},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5439578890800476},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4997069835662842},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4958532750606537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4941733181476593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4607032835483551},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44615015387535095},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44346413016319275},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43410515785217285},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4192134737968445},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3113276958465576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15096250176429749},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1995190897","https://openalex.org/W2013608223","https://openalex.org/W2018026382","https://openalex.org/W2025515167","https://openalex.org/W2044893557","https://openalex.org/W2062164080","https://openalex.org/W2069486713","https://openalex.org/W2069681747","https://openalex.org/W2103747981","https://openalex.org/W2109215269","https://openalex.org/W2121973264","https://openalex.org/W2145310550","https://openalex.org/W2149535104","https://openalex.org/W2164715564","https://openalex.org/W2187089797","https://openalex.org/W2236045036","https://openalex.org/W2397226255","https://openalex.org/W2403766732","https://openalex.org/W2550397165","https://openalex.org/W2559809918","https://openalex.org/W2606806821","https://openalex.org/W2747161606","https://openalex.org/W2962946126","https://openalex.org/W2963453742","https://openalex.org/W3013517569","https://openalex.org/W3127686677","https://openalex.org/W3147539069","https://openalex.org/W6712317276","https://openalex.org/W6713298849","https://openalex.org/W6775736700"],"related_works":["https://openalex.org/W3108403339","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W2162712524","https://openalex.org/W1955763106","https://openalex.org/W2025188156","https://openalex.org/W4287867034","https://openalex.org/W2175872006","https://openalex.org/W4375869276"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"the":[3,50,65,73,80,126,155,158,163,169,174],"generalization":[4,175],"of":[5,49,162],"speech":[6],"enhancement":[7],"algorithms":[8],"based":[9,39],"on":[10,168],"deep":[11],"neural":[12],"networks":[13],"(DNNs)":[14],"for":[15,68],"training":[16,32,42,139],"datasets":[17],"that":[18,72,112,122,151],"differ":[19],"in":[20,89],"size":[21],"and":[22,35,79,103,110,157],"diversity":[23],"is":[24,141],"analyzed.":[25],"For":[26],"this,":[27],"we":[28,119,149],"compare":[29],"noise":[30,40,51,66,75,83,171,178],"aware":[31,41],"(NAT)":[33],"features":[34,156],"signal-to-noise":[36],"ratio":[37],"(SNR)":[38],"(SNR-NAT)":[43],"features.":[44],"NAT":[45],"appends":[46],"an":[47],"estimate":[48],"power":[52],"spectral":[53],"density":[54],"(PSD)":[55],"to":[56,96,116,176],"a":[57,101,134],"noisy":[58],"periodogram":[59],"input":[60],"feature,":[61],"whereas":[62],"SNR-NAT":[63,124,153],"uses":[64],"PSD":[67],"normalization.":[69],"We":[70,99],"show":[71,111,121],"Hu":[74],"corpus":[76,84],"(limited":[77,85],"size)":[78],"CHiME":[81],"3":[82],"diversity)":[86],"may":[87],"result":[88],"DNNs":[90,115],"which":[91,172],"do":[92],"not":[93],"generalize":[94],"well":[95],"unseen":[97,177],"noises.":[98],"construct":[100],"large":[102],"diverse":[104,138],"dataset":[105],"from":[106],"freely":[107],"available":[108],"data":[109],"it":[113],"helps":[114],"generalize.":[117],"However,":[118],"also":[120],"with":[123],"features,":[125],"trained":[127],"models":[128],"are":[129,165],"more":[130],"robust":[131],"even":[132],"if":[133],"small":[135],"or":[136],"less":[137,166],"set":[140],"employed.":[142],"Using":[143],"t-distributed":[144],"stochastic":[145],"neighbor":[146],"embedding":[147],"(t-SNE),":[148],"demonstrate":[150],"using":[152],"both":[154],"resulting":[159],"internal":[160],"representation":[161],"DNN":[164],"dependent":[167],"background":[170],"facilitates":[173],"types.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}