{"id":"https://openalex.org/W2889373351","doi":"https://doi.org/10.21437/interspeech.2018-2441","title":"Investigations on Data Augmentation and Loss Functions for Deep Learning Based Speech-Background Separation","display_name":"Investigations on Data Augmentation and Loss Functions for Deep Learning Based Speech-Background Separation","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889373351","doi":"https://doi.org/10.21437/interspeech.2018-2441","mag":"2889373351"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2441","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3499","last_page":"3503"},"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":0.9987999796867371,"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":0.9983999729156494,"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/pesq","display_name":"PESQ","score":0.9118764400482178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7869732975959778},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7389105558395386},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.5836260914802551},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5474092364311218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5133418440818787},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.49416640400886536},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4759257137775421},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4607703387737274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4427633285522461},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4412899613380432},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4108163118362427},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3008749485015869},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.15674203634262085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11784914135932922}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9118764400482178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869732975959778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7389105558395386},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.5836260914802551},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5474092364311218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5133418440818787},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.49416640400886536},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4759257137775421},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4607703387737274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4427633285522461},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4412899613380432},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4108163118362427},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3008749485015869},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.15674203634262085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11784914135932922},{"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},{"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/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-2441","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W2031647436","https://openalex.org/W2062164080","https://openalex.org/W2078528584","https://openalex.org/W2101045344","https://openalex.org/W2124149378","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2460742184","https://openalex.org/W2609317876"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W4386746628","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"A":[0],"successful":[1],"deep":[2],"learning-based":[3],"method":[4],"for":[5,49,128],"separation":[6,53],"of":[7,23,38,60,81,88,98,122,134,159],"a":[8,90,120,144,178],"speech":[9,62,160],"signal":[10,16,152],"from":[11],"an":[12,39],"interfering":[13],"background":[14],"audio":[15],"is":[17,102],"based":[18,51],"on":[19,66,77,170],"neural":[20],"network":[21],"prediction":[22,130],"time-frequency":[24],"masks":[25],"which":[26,71,101],"multiply":[27],"noisy":[28],"signal\u2019s":[29],"short-time":[30],"Fourier":[31],"transform":[32],"(STFT)":[33],"to":[34,74,104,153,165],"yield":[35],"the":[36,58,67,86,166],"STFT":[37],"enhanced":[40],"signal.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,56],"investigate":[46,85],"training":[47,141],"strategies":[48],"mask-prediction":[50],"speech-background":[52],"systems.":[54],"First,":[55],"examine":[57],"impact":[59],"mixing":[61],"and":[63,124,131,136],"noise":[64],"\ufb01les":[65],"\ufb02y":[68],"during":[69],"training,":[70],"enables":[72],"models":[73],"be":[75],"trained":[76],"virtually":[78],"in\ufb01nite":[79],"amount":[80],"data.":[82],"We":[83,109],"also":[84],"effect":[87],"using":[89,177],"novel":[91,145],"signal-to-noise":[92],"ratio":[93,155],"related":[94],"loss":[95,146],"function,":[96],"instead":[97],"mean-squared":[99],"error":[100],"prone":[103],"scaling":[105],"differences":[106],"among":[107],"utterances.":[108],"evaluate":[110],"bi-directional":[111],"long-short":[112],"term":[113],"memory":[114],"(BLSTM)":[115],"networks":[116,127],"as":[117,119,163],"well":[118],"combination":[121],"convolutional":[123],"BLSTM":[125],"(CNN+BLSTM)":[126],"mask":[129,138],"compare":[132],"performances":[133],"real":[135],"complex-valued":[137],"prediction.":[139],"Data-augmented":[140],"combined":[142],"with":[143],"function":[147],"yields":[148],"signi\ufb01cant":[149],"improvements":[150],"in":[151],"distortion":[154],"(SDR)and":[156],"perceptual":[157],"evaluation":[158],"quality":[161],"(PESQ)":[162],"compared":[164],"best":[167],"published":[168],"result":[169],"CHiME-2":[171],"medium":[172],"vocabulary":[173],"data":[174],"set":[175],"when":[176],"CNN+BLSTM":[179],"network.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}