{"id":"https://openalex.org/W2940385941","doi":"https://doi.org/10.1109/icassp.2019.8683654","title":"Perceptually-motivated Environment-specific Speech Enhancement","display_name":"Perceptually-motivated Environment-specific Speech Enhancement","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2940385941","doi":"https://doi.org/10.1109/icassp.2019.8683654","mag":"2940385941"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683654","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":"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/A5101859099","display_name":"Jiaqi Su","orcid":"https://orcid.org/0000-0001-6038-0808"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Su","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034842939","display_name":"Adam Finkelstein","orcid":"https://orcid.org/0000-0001-9422-5363"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Finkelstein","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7015","last_page":"7019"},"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.831971287727356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7950266003608704},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.690081775188446},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6879594922065735},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6554607152938843},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5454928278923035},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5283475518226624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5006978511810303},{"id":"https://openalex.org/keywords/equalization","display_name":"Equalization (audio)","score":0.46262431144714355},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4311046600341797},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4256073236465454},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41059309244155884},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20011815428733826},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.13688203692436218},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12228149175643921},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1092943549156189},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10499635338783264}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.831971287727356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950266003608704},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.690081775188446},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6879594922065735},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6554607152938843},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5454928278923035},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5283475518226624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5006978511810303},{"id":"https://openalex.org/C75755367","wikidata":"https://www.wikidata.org/wiki/Q104531076","display_name":"Equalization (audio)","level":3,"score":0.46262431144714355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4311046600341797},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4256073236465454},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41059309244155884},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20011815428733826},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.13688203692436218},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12228149175643921},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1092943549156189},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10499635338783264},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683654","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":[{"id":"https://metadata.un.org/sdg/10","score":0.6000000238418579,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1897240248","https://openalex.org/W1924619199","https://openalex.org/W1989314204","https://openalex.org/W2006129368","https://openalex.org/W2044893557","https://openalex.org/W2086381917","https://openalex.org/W2120847449","https://openalex.org/W2121973264","https://openalex.org/W2141708418","https://openalex.org/W2153894152","https://openalex.org/W2164502538","https://openalex.org/W2401258970","https://openalex.org/W2408467190","https://openalex.org/W2519091744","https://openalex.org/W2542605056","https://openalex.org/W2577946330","https://openalex.org/W2711335087","https://openalex.org/W2793675140","https://openalex.org/W2800675406","https://openalex.org/W2802304149","https://openalex.org/W2886938596","https://openalex.org/W2889047169","https://openalex.org/W2889335976","https://openalex.org/W2889540509","https://openalex.org/W2962785568","https://openalex.org/W2962832181","https://openalex.org/W2963073614","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963420272","https://openalex.org/W2963539064","https://openalex.org/W2963782041","https://openalex.org/W2963920537","https://openalex.org/W2972824008","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W4294619240","https://openalex.org/W4296927107","https://openalex.org/W6640174519","https://openalex.org/W6712867848","https://openalex.org/W6732248266","https://openalex.org/W6735429107","https://openalex.org/W6748197083","https://openalex.org/W6757102092","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2016904525"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,13,38],"deep":[4],"learning":[5],"approach":[6,59],"to":[7,21],"enhance":[8],"speech":[9],"recordings":[10],"made":[11],"in":[12],"specific":[14],"environment.":[15],"A":[16],"single":[17],"neural":[18],"network":[19],"learns":[20],"ameliorate":[22],"several":[23],"types":[24],"of":[25],"recording":[26],"artifacts,":[27],"including":[28],"noise,":[29],"reverberation,":[30],"and":[31,52],"non-linear":[32],"equalization.":[33],"The":[34],"method":[35],"relies":[36],"on":[37,61],"new":[39],"perceptual":[40],"loss":[41,46],"function":[42],"that":[43,56],"combines":[44],"adversarial":[45],"with":[47],"spectrogram":[48],"features.":[49],"Both":[50],"subjective":[51],"objective":[53],"evaluations":[54],"show":[55],"the":[57],"proposed":[58],"improves":[60],"state-of-the-art":[62],"baseline":[63],"methods.":[64]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}