{"id":"https://openalex.org/W2152151492","doi":"https://doi.org/10.1109/icassp.2004.1326812","title":"Recent improvements of an auditory model based front-end for the transcription of vocal queries","display_name":"Recent improvements of an auditory model based front-end for the transcription of vocal queries","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2152151492","doi":"https://doi.org/10.1109/icassp.2004.1326812","mag":"2152151492"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5070960789","display_name":"Tom De Mulder","orcid":"https://orcid.org/0000-0003-0823-105X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"T. De Mulder","raw_affiliation_strings":["Department of Electronics and Information Systems (ELIS), Ghent University, Ghent, Belgium","[Dept. of Electron. & Information Syst., Ghent Univ., Gent, Belgium]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems (ELIS), Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"[Dept. of Electron. & Information Syst., Ghent Univ., Gent, Belgium]","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109066479","display_name":"J.-P. Martens","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"J.P. Martens","raw_affiliation_strings":["Department of Electronics and Information Systems (ELIS), Ghent University, Ghent, Belgium","[Dept. of Electron. & Information Syst., Ghent Univ., Gent, Belgium]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems (ELIS), Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"[Dept. of Electron. & Information Syst., Ghent Univ., Gent, Belgium]","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016215432","display_name":"Micheline Lesaffre","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"M. Lesaffre","raw_affiliation_strings":["Institute for Psychoacoustics and Electronic Music (IPEM), Ghent University, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Psychoacoustics and Electronic Music (IPEM), Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016185241","display_name":"Marc Leman","orcid":"https://orcid.org/0000-0002-9780-2194"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"M. Leman","raw_affiliation_strings":["Department of Applied Mathematics, Biometrics and Process Control, Ghent University, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Biometrics and Process Control, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012437460","display_name":"Bernard De Baets","orcid":"https://orcid.org/0000-0002-3876-620X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"B. De Baets","raw_affiliation_strings":["Department of Applied Mathematics, Biometrics and Process Control, Ghent University, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Biometrics and Process Control, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109967168","display_name":"H. De Meyer","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"H. De Meyer","raw_affiliation_strings":["Department of Applied Mathematics and Computer Science, Ghent University, Ghent, Belgium","Dept. of Applied Mathematics and Computer Science, Ghent University, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Computer Science, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Dept. of Applied Mathematics and Computer Science, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"iv","last_page":"257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9993000030517578,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8023324012756348},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.5628552436828613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5520093441009521},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5385274887084961},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5033580660820007},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.43259328603744507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2559042274951935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8023324012756348},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5628552436828613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5520093441009521},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5385274887084961},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5033580660820007},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.43259328603744507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2559042274951935},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2004.1326812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.6827","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.6827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ipem.ugent.be/MAMI/Public/Papers/DeMulderICASSP2004.pdf","raw_type":"text"},{"id":"pmh:oai:archive.ugent.be:404067","is_oa":false,"landing_page_url":"https://biblio.ugent.be/publication/404067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PROCEEDINGS","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1508603446","https://openalex.org/W1548678605","https://openalex.org/W1597330042","https://openalex.org/W1649161886","https://openalex.org/W1966280390","https://openalex.org/W1970992375","https://openalex.org/W1989164285","https://openalex.org/W2067128174","https://openalex.org/W2092387354","https://openalex.org/W2571123087","https://openalex.org/W6630420213","https://openalex.org/W6632736548","https://openalex.org/W6637056131","https://openalex.org/W6641901765"],"related_works":["https://openalex.org/W2783354812","https://openalex.org/W4384112194","https://openalex.org/W2103009189","https://openalex.org/W4312958259","https://openalex.org/W2349383066","https://openalex.org/W1969901537","https://openalex.org/W4328132048","https://openalex.org/W4308259661","https://openalex.org/W2028097510","https://openalex.org/W2544018345"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"recent":[3],"improvements":[4],"of":[5,13,25,34,43,55],"an":[6,80],"existing":[7],"acoustic":[8],"frontend":[9],"for":[10],"the":[11,23,32,40,44,57,60,72],"transcription":[12],"vocal":[14,77],"(hummed,":[15],"sung)":[16],"musical":[17],"queries":[18,78],"is":[19],"presented.":[20],"Thanks":[21],"to":[22,49,87],"addition":[24],"a":[26,35],"new":[27,73],"second":[28],"pitch":[29],"extractor":[30],"and":[31,52,91],"introduction":[33],"novel":[36],"multi-stage":[37],"segmentation":[38],"algorithm,":[39],"application":[41],"domain":[42],"front-end":[45],"could":[46,65],"be":[47,66],"extended":[48],"whistled":[50],"queries,":[51],"on":[53,59,100],"top":[54],"that,":[56],"performance":[58],"other":[61,96],"two":[62],"query":[63,103],"types":[64],"improved.":[67],"Experiments":[68],"have":[69],"shown":[70],"that":[71,92],"system":[74],"can":[75],"transcribe":[76],"with":[79],"accuracy":[81],"ranging":[82],"from":[83],"76":[84],"%":[85,89],"(whistling)":[86],"85":[88],"(humming),":[90],"it":[93],"clearly":[94],"outperforms":[95],"state-of-the":[97],"art":[98],"systems":[99],"all":[101],"three":[102],"types.":[104]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}