{"id":"https://openalex.org/W2175298729","doi":"https://doi.org/10.21437/interspeech.2015-454","title":"Comparison of forced-alignment speech recognition and humans for generating reference VAD","display_name":"Comparison of forced-alignment speech recognition and humans for generating reference VAD","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2175298729","doi":"https://doi.org/10.21437/interspeech.2015-454","mag":"2175298729"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-454","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/da/publications/31210b10-deeb-4de6-8951-0a67865b3c56","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027559803","display_name":"Ivan Kraljevski","orcid":"https://orcid.org/0000-0002-0670-4418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Kraljevski","raw_affiliation_strings":["voice INTER connect GmbH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"voice INTER connect GmbH","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Institut for Elektroniske Systemer"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut for Elektroniske Systemer","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011890683","display_name":"Maria Paola Bissiri","orcid":"https://orcid.org/0000-0003-2909-8841"},"institutions":[{"id":"https://openalex.org/I181656237","display_name":"Queen Margaret University","ror":"https://ror.org/002g3cb31","country_code":"GB","type":"education","lineage":["https://openalex.org/I181656237"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maria Paola Bissiri","raw_affiliation_strings":["Queen Margaret University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Margaret University","institution_ids":["https://openalex.org/I181656237"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.05930247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2937","last_page":"2941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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/T12031","display_name":"Speech and dialogue systems","score":0.9959999918937683,"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":0.7502682209014893},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6768088936805725},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37263965606689453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34079045057296753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7502682209014893},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6768088936805725},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37263965606689453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34079045057296753}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2015-454","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/31210b10-deeb-4de6-8951-0a67865b3c56","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/31210b10-deeb-4de6-8951-0a67865b3c56","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kraljevski, I, Tan, Z-H & Paola Bissiri, M 2015, Comparison of Forced-Alignment Speech Recognition and Humans for Generating Reference VAD. in INTERSPEECH-2015. ISCA, INTERSPEECH , pp. 2937-2941, INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, 06/09/2015. < http://www.isca-speech.org/archive/interspeech_2015/i15_2937.html >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:eresearch.qmu.ac.uk:4422","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402028","display_name":"Queen Margaret University Publications Repository (Queen Margaret University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I181656237","host_organization_name":"Queen Margaret University","host_organization_lineage":["https://openalex.org/I181656237"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:eresearch.qmu.ac.uk:20.500.12289/4422","is_oa":true,"landing_page_url":"https://eresearch.qmu.ac.uk/handle/20.500.12289/4422","pdf_url":"https://eresearch.qmu.ac.uk/handle/20.500.12289/4422","source":{"id":"https://openalex.org/S4306402028","display_name":"Queen Margaret University Publications Repository (Queen Margaret University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I181656237","host_organization_name":"Queen Margaret University","host_organization_lineage":["https://openalex.org/I181656237"],"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":"article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/31210b10-deeb-4de6-8951-0a67865b3c56","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/31210b10-deeb-4de6-8951-0a67865b3c56","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kraljevski, I, Tan, Z-H & Paola Bissiri, M 2015, Comparison of Forced-Alignment Speech Recognition and Humans for Generating Reference VAD. in INTERSPEECH-2015. ISCA, INTERSPEECH , pp. 2937-2941, INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, 06/09/2015. < http://www.isca-speech.org/archive/interspeech_2015/i15_2937.html >","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.47999998927116394,"display_name":"Reduced inequalities"},{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W91754172","https://openalex.org/W1563939609","https://openalex.org/W1583049097","https://openalex.org/W2054665642","https://openalex.org/W2115008841","https://openalex.org/W2117468249","https://openalex.org/W2119573952","https://openalex.org/W2129120544","https://openalex.org/W2152181798","https://openalex.org/W2156885227","https://openalex.org/W2161964681","https://openalex.org/W2169711598","https://openalex.org/W2404979693","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"present":[1],"paper":[2],"aims":[3],"to":[4,18],"answer":[5],"the":[6,31,40,57,61],"question":[7],"whether":[8],"forced-alignment":[9,69],"speech":[10,70],"recognition":[11,71],"can":[12,72],"be":[13],"used":[14],"as":[15],"an":[16],"alternative":[17],"humans":[19],"in":[20],"generating":[21],"reference":[22,41],"Voice":[23],"Activity":[24],"Detection":[25],"(VAD)":[26],"transcriptions.":[27,64],"An":[28],"investigation":[29],"of":[30,33],"level":[32],"agreement":[34],"between":[35],"automatic/manual":[36],"VAD":[37,77],"transcriptions":[38],"and":[39,60,75],"ones":[42],"produced":[43,59],"by":[44],"a":[45],"human":[46],"expert":[47],"was":[48,54],"carried":[49],"out.":[50],"Thereafter,":[51],"statistical":[52],"analysis":[53],"employed":[55],"on":[56],"automatically":[58],"collected":[62],"manual":[63],"Experimental":[65],"results":[66],"confirmed":[67],"that":[68],"provide":[73],"accurate":[74],"consistent":[76],"labels.":[78]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}