{"id":"https://openalex.org/W4372349390","doi":"https://doi.org/10.1109/icassp49357.2023.10097075","title":"On Batching Variable Size Inputs for Training End-to-End Speech Enhancement Systems","display_name":"On Batching Variable Size Inputs for Training End-to-End Speech Enhancement Systems","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349390","doi":"https://doi.org/10.1109/icassp49357.2023.10097075"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097075","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5103167575","display_name":"Philippe Gonzalez","orcid":"https://orcid.org/0009-0006-4965-3514"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Philippe Gonzalez","raw_affiliation_strings":["Technical University of Denmark,Department of Health Technology","Department of Health Technology, Technical University of Denmark"],"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Department of Health Technology","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064146030","display_name":"Tommy Sonne Alstr\u00f8m","orcid":"https://orcid.org/0000-0003-0941-3146"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tommy Sonne Alstr\u00f8m","raw_affiliation_strings":["Technical University of Denmark,Department of Applied Mathematics and Computer Science","Department of Applied Mathematics and Computer Science, Technical University of Denmark"],"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Department of Applied Mathematics and Computer Science","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"Department of Applied Mathematics and Computer Science, Technical University of Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052043106","display_name":"Tobias May","orcid":"https://orcid.org/0000-0002-5463-5509"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tobias May","raw_affiliation_strings":["Technical University of Denmark,Department of Health Technology","Department of Health Technology, Technical University of Denmark"],"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Department of Health Technology","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103167575"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":1.4473,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81882429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"41","issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7748132944107056},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5276008248329163},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5183459520339966},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49117419123649597},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.4424659311771393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22514915466308594},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08983102440834045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748132944107056},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5276008248329163},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5183459520339966},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49117419123649597},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.4424659311771393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22514915466308594},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08983102440834045},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097075","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/8","score":0.4099999964237213,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1806891645","https://openalex.org/W1974387177","https://openalex.org/W1997836753","https://openalex.org/W2054480978","https://openalex.org/W2114218864","https://openalex.org/W2199505332","https://openalex.org/W2364134690","https://openalex.org/W2404126548","https://openalex.org/W2516001803","https://openalex.org/W2528993343","https://openalex.org/W2633911929","https://openalex.org/W2748584437","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963933775","https://openalex.org/W2963959597","https://openalex.org/W2964243274","https://openalex.org/W3027637851","https://openalex.org/W3035790469","https://openalex.org/W3099330747","https://openalex.org/W3105037130","https://openalex.org/W3120954100","https://openalex.org/W3197549883","https://openalex.org/W3198680319","https://openalex.org/W3205004157","https://openalex.org/W4213196139","https://openalex.org/W4232282348","https://openalex.org/W4285503945","https://openalex.org/W4295334694","https://openalex.org/W4393776813","https://openalex.org/W4393792386","https://openalex.org/W6631190155","https://openalex.org/W6656414902","https://openalex.org/W6726983090","https://openalex.org/W6738435047","https://openalex.org/W6777701575","https://openalex.org/W6796651418","https://openalex.org/W6802938626","https://openalex.org/W6803075754","https://openalex.org/W6912458518"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"The":[0],"performance":[1,105,130,152,183],"of":[2,87,95,116,131],"neural":[3],"network-based":[4],"speech":[5,37,128],"enhancement":[6,129],"systems":[7],"is":[8,46,106],"primarily":[9,23],"influenced":[10],"by":[11,25],"the":[12,30,93,114,124],"model":[13],"architecture,":[14],"whereas":[15],"training":[16,26,125,150,174],"times":[17],"and":[18,35,70,73,101,120,127,138,176],"computational":[19],"resource":[20,99],"utilization":[21,100],"are":[22],"affected":[24],"parameters":[27],"such":[28],"as":[29],"batch":[31,80,121,147,169,191],"size.":[32,192],"Since":[33],"noisy":[34],"reverberant":[36],"mixtures":[38],"can":[39,74],"have":[40],"different":[41,117],"duration,":[42],"a":[43,66,78,83,132,145,167,189],"batching":[44,118,158,165,187],"strategy":[45],"required":[47],"to":[48,185],"handle":[49],"variable":[50],"size":[51,81,148,170],"inputs":[52],"during":[53,149],"training,":[54],"in":[55,89,135,153],"particular":[56],"for":[57,65,82,156,172],"state-of-the-art":[58],"end-to-end":[59],"systems.":[60],"Such":[61],"strategies":[62,97,119],"usually":[63],"strive":[64],"compromise":[67],"between":[68],"zero-padding":[69],"data":[71,88],"randomization,":[72],"be":[75],"combined":[76],"with":[77,166,188],"dynamic":[79,168],"more":[84,102],"consistent":[85],"amount":[86],"each":[90],"batch.":[91],"However,":[92],"effect":[94,115],"these":[96],"on":[98,123],"importantly":[103],"network":[104],"not":[107],"well":[108],"documented.":[109],"This":[110],"paper":[111],"systematically":[112],"investigates":[113],"sizes":[122],"statistics":[126],"Conv-TasNet,":[133],"evaluated":[134],"both":[136,154],"matched":[137],"mismatched":[139],"conditions.":[140],"We":[141],"find":[142],"that":[143],"using":[144,161],"small":[146],"improves":[151],"conditions":[155],"all":[157],"strategies.":[159],"Moreover,":[160],"sorted":[162],"or":[163],"bucket":[164],"allows":[171],"reduced":[173],"time":[175],"GPU":[177],"memory":[178],"usage":[179],"while":[180],"achieving":[181],"similar":[182],"compared":[184],"random":[186],"fixed":[190]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}