{"id":"https://openalex.org/W2691405956","doi":"https://doi.org/10.1109/icassp.2017.7953214","title":"Voice-transformation-based data augmentation for prosodic classification","display_name":"Voice-transformation-based data augmentation for prosodic classification","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2691405956","doi":"https://doi.org/10.1109/icassp.2017.7953214","mag":"2691405956"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5003690515","display_name":"Raul Castro Fernandez","orcid":"https://orcid.org/0000-0001-7675-6080"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raul Fernandez","raw_affiliation_strings":["IBM TJ Watson Research Center, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["IBM TJ Watson Research Center, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029658066","display_name":"A. S. Sorin","orcid":"https://orcid.org/0000-0002-9775-2115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Sorin","raw_affiliation_strings":["IBM Haifa Research Labs, Haifa, Haifa, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Haifa Research Labs, Haifa, Haifa, IL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM TJ Watson Research Center, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053864983","display_name":"Ron Hoory","orcid":"https://orcid.org/0009-0006-1327-5160"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ron Hoory","raw_affiliation_strings":["IBM Haifa Research Lab, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Haifa Research Lab, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5530","last_page":"5534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.7608203887939453},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6795133352279663},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6750140190124512},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6120377779006958},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5869807004928589},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5854518413543701},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5379944443702698},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5207881331443787},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.517238199710846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5033265948295593},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4203755855560303},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.41241714358329773},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3691738247871399},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.117926687002182},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08522647619247437},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.08165758848190308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608203887939453},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6795133352279663},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6750140190124512},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6120377779006958},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5869807004928589},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5854518413543701},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5379944443702698},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5207881331443787},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.517238199710846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5033265948295593},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4203755855560303},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.41241714358329773},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3691738247871399},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.117926687002182},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08522647619247437},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.08165758848190308},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W28194048","https://openalex.org/W135060498","https://openalex.org/W169745891","https://openalex.org/W272567777","https://openalex.org/W1012287703","https://openalex.org/W1024956260","https://openalex.org/W1045138520","https://openalex.org/W1598092087","https://openalex.org/W1599201313","https://openalex.org/W1604451795","https://openalex.org/W1647142869","https://openalex.org/W1810943226","https://openalex.org/W1870253808","https://openalex.org/W1881513295","https://openalex.org/W1910140552","https://openalex.org/W1915522689","https://openalex.org/W1924770834","https://openalex.org/W1942690640","https://openalex.org/W2039285212","https://openalex.org/W2088670089","https://openalex.org/W2094133503","https://openalex.org/W2099621636","https://openalex.org/W2103069945","https://openalex.org/W2107459631","https://openalex.org/W2109292858","https://openalex.org/W2120850838","https://openalex.org/W2131342371","https://openalex.org/W2143678303","https://openalex.org/W2170012275","https://openalex.org/W2283759102","https://openalex.org/W2290962344","https://openalex.org/W2398538797","https://openalex.org/W2421050884","https://openalex.org/W2512137286","https://openalex.org/W2515737026","https://openalex.org/W2516354030","https://openalex.org/W2595150118","https://openalex.org/W2963110542","https://openalex.org/W2963543871","https://openalex.org/W4285719527","https://openalex.org/W4299951565","https://openalex.org/W6601083237","https://openalex.org/W6635586287","https://openalex.org/W6638273328","https://openalex.org/W6640212811","https://openalex.org/W6675409298","https://openalex.org/W6712784995"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W2334135487","https://openalex.org/W4298046075","https://openalex.org/W4207066001","https://openalex.org/W2381837697","https://openalex.org/W4251666207","https://openalex.org/W2087397317","https://openalex.org/W2350046259","https://openalex.org/W2089671023"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3],"explore":[4],"data-augmentation":[5],"techniques":[6],"for":[7,87,120],"the":[8,12,35,40,48,54,63,66,72,83,102,110,118],"task":[9],"of":[10,14,53,65,74,85,95,113],"improving":[11,69],"performance":[13,70],"a":[15,106],"supervised":[16],"recurrent-neural-network":[17],"classifier":[18],"tasked":[19],"with":[20],"predicting":[21],"prosodic-boundary":[22],"and":[23,43,50,115,122],"pitch-accent":[24],"labels.":[25],"The":[26],"technique":[27],"is":[28,78],"based":[29],"on":[30,117],"applying":[31],"voice":[32],"transformations":[33],"to":[34,56,98],"training":[36,59,103],"data":[37],"that":[38],"modify":[39],"pitch":[41],"baseline":[42],"range,":[44],"as":[45,47,90,92],"well":[46,91],"vocal-tract":[49],"vocal-source":[51],"characteristics":[52],"speakers":[55,99],"generate":[57],"further":[58],"examples.":[60],"We":[61],"demonstrate":[62],"validity":[64],"approach":[67],"by":[68],"when":[71],"amount":[73],"base":[75],"labeled":[76],"examples":[77],"small":[79],"(showing":[80,105],"reductions":[81],"in":[82,93,101,109,126],"range":[84],"7%\u201312%":[86],"reduced-data":[88],"conditions)":[89],"terms":[94],"its":[96],"generalization":[97],"unseen":[100],"set":[104],"relative":[107],"reduction":[108],"error":[111],"rate":[112],"8.74%":[114],"4.75%,":[116],"average,":[119],"boundaries":[121],"accent":[123],"tasks":[124],"respectively,":[125],"leave-one-speaker-out":[127],"validation).":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}