{"id":"https://openalex.org/W2940290905","doi":"https://doi.org/10.1109/icassp.2019.8682367","title":"Learning Bandwidth Expansion Using Perceptually-motivated Loss","display_name":"Learning Bandwidth Expansion Using Perceptually-motivated Loss","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2940290905","doi":"https://doi.org/10.1109/icassp.2019.8682367","mag":"2940290905"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682367","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/A5003656942","display_name":"Berthy T. Feng","orcid":"https://orcid.org/0000-0002-1843-2165"},"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":"Berthy Feng","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/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"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":"Zeyu Jin","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/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":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1696,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88173352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.994700014591217,"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":0.9919000267982483,"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/bandwidth","display_name":"Bandwidth (computing)","score":0.7665178179740906},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7486865520477295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5353192687034607},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.4805757999420166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4740602374076843},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3400576710700989},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09522882103919983},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09291896224021912}],"concepts":[{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.7665178179740906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486865520477295},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5353192687034607},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.4805757999420166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4740602374076843},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3400576710700989},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09522882103919983},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09291896224021912},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682367","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":40,"referenced_works":["https://openalex.org/W99802290","https://openalex.org/W204144752","https://openalex.org/W1493163583","https://openalex.org/W1517841224","https://openalex.org/W1531967940","https://openalex.org/W2086381917","https://openalex.org/W2100285470","https://openalex.org/W2141708418","https://openalex.org/W2397254463","https://openalex.org/W2399077117","https://openalex.org/W2399742709","https://openalex.org/W2400830530","https://openalex.org/W2518315489","https://openalex.org/W2519091744","https://openalex.org/W2536224642","https://openalex.org/W2567070169","https://openalex.org/W2584032004","https://openalex.org/W2739619458","https://openalex.org/W2769810959","https://openalex.org/W2784918340","https://openalex.org/W2802034954","https://openalex.org/W2889905534","https://openalex.org/W2890648862","https://openalex.org/W2890983311","https://openalex.org/W2892335023","https://openalex.org/W2949382160","https://openalex.org/W2963103134","https://openalex.org/W2963782041","https://openalex.org/W2963952344","https://openalex.org/W2963970792","https://openalex.org/W3122318757","https://openalex.org/W4294619240","https://openalex.org/W6604083050","https://openalex.org/W6712300757","https://openalex.org/W6712911448","https://openalex.org/W6713030564","https://openalex.org/W6731370813","https://openalex.org/W6732429163","https://openalex.org/W6741681139","https://openalex.org/W6950332740"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W4319862422","https://openalex.org/W2042327336","https://openalex.org/W1971598839","https://openalex.org/W3144767625","https://openalex.org/W2017964352","https://openalex.org/W3207737697","https://openalex.org/W2097303478","https://openalex.org/W2006045908","https://openalex.org/W2023720074"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,14,26],"perceptually":[3],"motivated":[4],"approach":[5],"to":[6],"bandwidth":[7,55],"expansion":[8],"for":[9,53],"speech.":[10],"Our":[11],"method":[12],"pairs":[13],"new":[15],"3-way":[16],"split":[17],"variant":[18],"of":[19],"the":[20,34],"FFTNet":[21],"neural":[22],"vocoder":[23],"structure":[24],"with":[25],"perceptual":[27],"loss":[28],"function,":[29],"combining":[30],"objectives":[31],"from":[32,49],"both":[33,50],"time":[35],"and":[36],"frequency":[37],"domains.":[38],"Mean":[39],"opinion":[40],"score":[41],"tests":[42],"show":[43],"that":[44],"it":[45],"outperforms":[46],"baseline":[47],"methods":[48],"domains,":[51],"even":[52],"extreme":[54],"expansion.":[56]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
