{"id":"https://openalex.org/W2973066235","doi":"https://doi.org/10.21437/interspeech.2019-2984","title":"Prosodic Representations of Prominence Classification Neural Networks and Autoencoders Using Bottleneck Features","display_name":"Prosodic Representations of Prominence Classification Neural Networks and Autoencoders Using Bottleneck Features","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2973066235","doi":"https://doi.org/10.21437/interspeech.2019-2984","mag":"2973066235"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2984","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10138/312019","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063704331","display_name":"Sofoklis Kakouros","orcid":"https://orcid.org/0000-0001-8996-0793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sofoklis Kakouros","raw_affiliation_strings":["Department of Digital Humanities"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Digital Humanities","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009644866","display_name":"Antti Suni","orcid":"https://orcid.org/0000-0003-3414-6035"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antti Suni","raw_affiliation_strings":["Phonetics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phonetics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081754009","display_name":"Juraj \u0160imko","orcid":"https://orcid.org/0000-0002-8693-9646"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juraj \u0160imko","raw_affiliation_strings":["Phonetics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phonetics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040474925","display_name":"Martti Vainio","orcid":"https://orcid.org/0000-0003-2570-0196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martti Vainio","raw_affiliation_strings":["Phonetics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phonetics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1446,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58473908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1946","last_page":"1950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8004999756813049,"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":0.8004999756813049,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.7366999983787537,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.6797000169754028,"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/bottleneck","display_name":"Bottleneck","score":0.785839319229126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6462522745132446},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6363654732704163},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5438490509986877},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3719186782836914},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36484983563423157},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3565613031387329}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.785839319229126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6462522745132446},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6363654732704163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5438490509986877},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3719186782836914},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36484983563423157},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3565613031387329},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-2984","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:helda.helsinki.fi:10138/312019","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/312019","pdf_url":"http://hdl.handle.net/10138/312019","source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:helda.helsinki.fi:10138/312019","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/312019","pdf_url":"http://hdl.handle.net/10138/312019","source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2973066235.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"Prominence":[0],"perception":[1],"has":[2],"been":[3,60],"known":[4],"to":[5,45,62],"correlate":[6],"with":[7,146],"a":[8,140],"complex":[9,87],"interplay":[10],"of":[11,15,27,29,93,110,142,168,177],"the":[12,50,69,86,94,99,105,120,124,155,160,169,178,182,186],"acoustic":[13,70,107],"features":[14,31,88,102],"energy,":[16],"fundamental":[17],"frequency,":[18],"spectral":[19],"tilt,":[20],"and":[21,25,36,47,55,79,113,118,162,185],"duration.":[22],"The":[23,135],"contribution":[24],"importance":[26],"each":[28],"these":[30],"in":[32,39,114],"distinguishing":[33],"between":[34],"prominent":[35],"non-prominent":[37],"units":[38],"speech":[40,145],"is":[41],"not":[42],"always":[43],"easy":[44],"determine,":[46],"more":[48],"so,":[49],"prosodic":[51,71,108,156],"representations":[52,72,157],"that":[53,73,154],"humans":[54],"automatic":[56],"classifiers":[57],"learn":[58,81],"have":[59],"difficult":[61],"interpret.":[63],"This":[64],"work":[65],"focuses":[66],"on":[67,139],"examining":[68],"binary":[74],"prominence":[75,111,125,149,171],"classification":[76,126],"neural":[77,127],"networks":[78,128],"autoencoders":[80],"for":[82,104,181,191],"prominence.":[83],"We":[84,116],"investigate":[85],"learned":[89],"at":[90],"different":[91,175],"layers":[92],"network":[95,133],"as":[96,98,129,131],"well":[97,130],"10-dimensional":[100],"bottleneck":[101],"(BNFs),":[103],"standard":[106],"correlates":[109],"separately":[112],"combination.":[115],"analyze":[117],"visualize":[119],"BNFs":[121,161],"obtained":[122,158,190],"from":[123,159],"their":[132],"activations.":[134],"experiments":[136],"are":[137],"conducted":[138],"corpus":[141],"Dutch":[143],"continuous":[144],"manually":[147],"annotated":[148],"labels.":[150],"Our":[151],"results":[152],"show":[153],"higher-dimensional":[163],"non-BNFs":[164],"provide":[165],"good":[166],"separation":[167,189],"two":[170],"categories,":[172],"with,":[173],"however,":[174],"partitioning":[176],"BNF":[179],"space":[180],"distinct":[183],"features,":[184],"best":[187],"overall":[188],"F0.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}