{"id":"https://openalex.org/W2939051810","doi":"https://doi.org/10.1109/icassp.2019.8683041","title":"Data Augmentation Strategies for Neural Network F0 Estimation","display_name":"Data Augmentation Strategies for Neural Network F0 Estimation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939051810","doi":"https://doi.org/10.1109/icassp.2019.8683041","mag":"2939051810"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683041","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":"https://research.aalto.fi/files/33983314/ELEC_Airaksinen_Data_augmentation_ICASSP19.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013722514","display_name":"Manu Airaksinen","orcid":"https://orcid.org/0000-0002-8031-2260"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"funder","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Manu Airaksinen","raw_affiliation_strings":["Department of Clinical Neurophysiology, University of Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Clinical Neurophysiology, University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081575688","display_name":"Lauri Juvela","orcid":"https://orcid.org/0000-0002-2201-103X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"funder","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lauri Juvela","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"funder","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016518233","display_name":"Okko R\u00e4s\u00e4nen","orcid":"https://orcid.org/0000-0002-0537-0946"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"funder","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Okko Rasanen","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.353,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":13,"citation_normalized_percentile":{"value":0.656933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":88},"biblio":{"volume":null,"issue":null,"first_page":"6485","last_page":"6489"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998,"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":0.9998,"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":0.9997,"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/T11309","display_name":"Music and Audio Processing","score":0.9996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness","score":0.8109442},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5941613},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.45192453},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.4489165},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43985426}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8109442},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8038092},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6591941},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6096562},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5941613},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5245105},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.45192453},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.4489165},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43985426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37660748},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3311717},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14420402},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683041","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/38336","pdf_url":"https://research.aalto.fi/files/33983314/ELEC_Airaksinen_Data_augmentation_ICASSP19.pdf","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":["Aalto University"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/38336","pdf_url":"https://research.aalto.fi/files/33983314/ELEC_Airaksinen_Data_augmentation_ICASSP19.pdf","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":["Aalto University"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false},"sustainable_development_goals":[{"score":0.46,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W181056519","https://openalex.org/W1974387177","https://openalex.org/W2091425152","https://openalex.org/W2096429026","https://openalex.org/W2099621636","https://openalex.org/W2118774185","https://openalex.org/W2129142580","https://openalex.org/W2397375888","https://openalex.org/W2403891086","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2618416693","https://openalex.org/W2752143737","https://openalex.org/W2803229097","https://openalex.org/W2914312680","https://openalex.org/W2962866891","https://openalex.org/W2963050807","https://openalex.org/W2963446712","https://openalex.org/W2963996777","https://openalex.org/W2964121744","https://openalex.org/W3098357269","https://openalex.org/W3127686677","https://openalex.org/W328913250","https://openalex.org/W4206319965"],"related_works":["https://openalex.org/W4254341835","https://openalex.org/W35292311","https://openalex.org/W2803166627","https://openalex.org/W2617269004","https://openalex.org/W2099204336","https://openalex.org/W2079194684","https://openalex.org/W2046073792","https://openalex.org/W1972544579","https://openalex.org/W1748856376","https://openalex.org/W1591384192"],"abstract_inverted_index":{"This":[0],"study":[1],"explores":[2],"various":[3],"speech":[4],"data":[5,67],"augmentation":[6,22,31,35,91,119],"methods":[7,137],"for":[8,54],"the":[9,47,57,65,79,83,98,133],"task":[10],"of":[11,49,56,71,78,101,140],"noise-robust":[12],"fundamental":[13],"frequency":[14],"(F0)":[15],"estimation":[16,136],"with":[17],"neural":[18,58],"networks.":[19],"The":[20,127],"explored":[21],"strategies":[23],"are":[24],"split":[25],"into":[26,33],"additive":[27],"noise":[28,88,99,141],"and":[29,32,74,89,104],"channel-based":[30],"vocoder-based":[34,38,106,117],"methods.":[36],"In":[37],"augmentation,":[39],"a":[40],"glottal":[41],"vocoder":[42],"is":[43],"used":[44,53,94,123],"to":[45,63,95,124],"enhance":[46],"accuracy":[48],"ground":[50,107],"truth":[51,108],"F0":[52,72,135],"training":[55,66],"network,":[59],"as":[60,62],"well":[61],"expand":[64],"diversity":[68,118],"in":[69,138],"terms":[70,139],"patterns":[73],"vocal":[75],"tract":[76],"lengths":[77],"talkers.":[80],"Evaluations":[81],"on":[82],"PTDB-TUG":[84],"corpus":[85],"indicate":[86],"that":[87,105],"channel":[90],"can":[92,120],"be":[93,122],"greatly":[96,131],"increase":[97,125],"robustness":[100],"trained":[102],"models,":[103],"enhancement":[109],"further":[110],"increases":[111],"model":[112],"performance.":[113,126],"For":[114],"smaller":[115],"datasets,":[116],"also":[121],"best-performing":[128],"proposed":[129],"method":[130],"outperformed":[132],"compared":[134],"robustness.":[142]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2939051810","counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1}],"updated_date":"2025-04-17T16:24:00.971728","created_date":"2019-04-25"}