{"id":"https://openalex.org/W2736419256","doi":"https://doi.org/10.21437/interspeech.2017-1115","title":"Automatic Construction of the Finnish Parliament Speech Corpus","display_name":"Automatic Construction of the Finnish Parliament Speech Corpus","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2736419256","doi":"https://doi.org/10.21437/interspeech.2017-1115","mag":"2736419256"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1115","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/b1ffce87-0beb-4c3c-89e5-a0adfdbaf1f6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057537776","display_name":"Andr\u00e9 Mansikkaniemi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Andr\u00e9 Mansikkaniemi","raw_affiliation_strings":["Department of Signal Processing and Acoustics"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074707861","display_name":"Peter Smit","orcid":"https://orcid.org/0000-0001-7611-1477"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Smit","raw_affiliation_strings":["Department of Signal Processing and Acoustics"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":["Department of Signal Processing and Acoustics"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057537776"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7201,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92388278,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3762","last_page":"3766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9921000003814697,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9908000230789185,"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/computer-science","display_name":"Computer science","score":0.738095760345459},{"id":"https://openalex.org/keywords/parliament","display_name":"Parliament","score":0.7238534688949585},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5725701451301575},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.491384893655777},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4241350293159485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41383013129234314},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2627633213996887},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.1248590350151062},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07435503602027893},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.06113386154174805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738095760345459},{"id":"https://openalex.org/C2781440851","wikidata":"https://www.wikidata.org/wiki/Q35749","display_name":"Parliament","level":3,"score":0.7238534688949585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5725701451301575},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.491384893655777},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4241350293159485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41383013129234314},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2627633213996887},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1248590350151062},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07435503602027893},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.06113386154174805}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2017-1115","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/28277","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/b1ffce87-0beb-4c3c-89e5-a0adfdbaf1f6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":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":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/28277","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/b1ffce87-0beb-4c3c-89e5-a0adfdbaf1f6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":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":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W203760253","https://openalex.org/W851005513","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2070737455","https://openalex.org/W2117621558","https://openalex.org/W2142937603","https://openalex.org/W2156700117","https://openalex.org/W2160815625","https://openalex.org/W2251459480","https://openalex.org/W2293596383","https://openalex.org/W2397159106","https://openalex.org/W2401896149","https://openalex.org/W2514741789"],"related_works":["https://openalex.org/W2023822311","https://openalex.org/W4252661029","https://openalex.org/W2375791221","https://openalex.org/W2254312451","https://openalex.org/W4365503523","https://openalex.org/W2097613883","https://openalex.org/W589623597","https://openalex.org/W4312908577","https://openalex.org/W2569479847","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,10,22,62,134,160,169,188],"recognition":[2,189],"(ASR)":[3],"systems":[4,31],"require":[5],"large":[6],"amounts":[7],"of":[8,44,60,79,82,166,176,191],"transcribed":[9,61],"data,":[11],"for":[12,63],"training":[13,45],"state-of-the-art":[14],"deep":[15],"neural":[16],"network":[17],"(DNN)":[18],"acoustic":[19,113],"models.":[20],"Transcribed":[21],"is":[23,40,124,138,155],"a":[24,42,54,131],"scarce":[25],"and":[26,29,56,67,72,93,122,151],"expensive":[27],"resource,":[28],"ASR":[30,105],"are":[32,88,115],"prone":[33],"to":[34,101,126,161,183],"underperform":[35],"in":[36,179,187],"domains":[37],"where":[38],"there":[39],"not":[41],"lot":[43],"data":[46],"available.":[47],"In":[48],"this":[49],"work,":[50],"we":[51],"open":[52],"up":[53],"vast":[55],"previously":[57],"unused":[58],"resource":[59],"Finnish,":[64],"by":[65,96,144],"retrieving":[66],"aligning":[68],"all":[69],"the":[70,76,80,91,98,103,108,118,146,163,167,174],"recordings":[71],"meeting":[73,110,177],"transcripts":[74,178],"from":[75,90],"web":[77],"portal":[78],"Parliament":[81],"Finland.":[83],"Short":[84],"speech-text":[85],"segment":[86],"pairs":[87],"retrieved":[89],"audio":[92],"text":[94],"material,":[95],"using":[97],"Levenshtein":[99],"algorithm":[100],"align":[102],"first-pass":[104],"hypotheses":[106],"with":[107],"corresponding":[109],"transcripts.":[111],"DNN":[112],"models":[114,128],"trained":[116,129],"on":[117,130,140,158],"automatically":[119],"constructed":[120],"corpus,":[121],"performance":[123,137],"compared":[125],"other":[127],"commercially":[132],"available":[133],"corpus.":[135,170],"Model":[136],"evaluated":[139,157],"Finnish":[141,192],"parliament":[142,168,193],"speech,":[143],"dividing":[145],"testing":[147],"set":[148],"into":[149],"seen":[150],"unseen":[152],"speakers.":[153],"Performance":[154],"also":[156,172],"broadcast":[159],"test":[162],"general":[164],"applicability":[165],"We":[171],"study":[173],"use":[175],"language":[180],"model":[181],"adaptation,":[182],"achieve":[184],"additional":[185],"gains":[186],"accuracy":[190],"speech.":[194]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
