{"id":"https://openalex.org/W2093509768","doi":"https://doi.org/10.1109/icassp.2010.5495974","title":"Perceptual audio features for unsupervised key-phrase detection","display_name":"Perceptual audio features for unsupervised key-phrase detection","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W2093509768","doi":"https://doi.org/10.1109/icassp.2010.5495974","mag":"2093509768"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","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/A5032452504","display_name":"Dirk von Zeddelmann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166245","display_name":"Fraunhofer Institute for Communication, Information Processing and Ergonomics","ror":"https://ror.org/05nn0gw40","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210166245","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dirk von Zeddelmann","raw_affiliation_strings":["Fraunhofer-FKIE, KOM Department, 53343 Wachtberg, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer-FKIE, KOM Department, 53343 Wachtberg, Germany","institution_ids":["https://openalex.org/I4210166245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009152780","display_name":"Frank Kurth","orcid":"https://orcid.org/0000-0002-9992-083X"},"institutions":[{"id":"https://openalex.org/I4210166245","display_name":"Fraunhofer Institute for Communication, Information Processing and Ergonomics","ror":"https://ror.org/05nn0gw40","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210166245","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Kurth","raw_affiliation_strings":["Fraunhofer-FKIE, KOM Department, 53343 Wachtberg, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer-FKIE, KOM Department, 53343 Wachtberg, Germany","institution_ids":["https://openalex.org/I4210166245"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109881851","display_name":"Meinard M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meinard Muller","raw_affiliation_strings":["Saarland University and MPI Informatik, Campus E1 4, 66123 Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Saarland University and MPI Informatik, Campus E1 4, 66123 Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712","https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032452504"],"corresponding_institution_ids":["https://openalex.org/I4210166245"],"apc_list":null,"apc_paid":null,"fwci":3.3716,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.92835376,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"257","last_page":"260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.8171826601028442},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7033978700637817},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.688112199306488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6018785238265991},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5902162790298462},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4921490550041199},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49002206325531006},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.46922311186790466},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.46404120326042175},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41372209787368774},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33033764362335205}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8171826601028442},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7033978700637817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.688112199306488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6018785238265991},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5902162790298462},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4921490550041199},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49002206325531006},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.46922311186790466},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.46404120326042175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41372209787368774},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33033764362335205},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp.2010.5495974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.400.487","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.400.487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://domino.mpi-inf.mpg.de/intranet/ag4/ag4publ.nsf/0/3856273C06036C38C125775400559262/$file/2010_ZeddelmannKurthMueller_KeyphraseDetection_ICASSP.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:537292","is_oa":false,"landing_page_url":"http://edoc.mpg.de/537292","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scott, Douglas C.: 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2010). - Pt. 1, IEEE, 257-260 (2010)","raw_type":"Conference-Paper"},{"id":"pmh:oai:fraunhofer.de:N-188656","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-188656.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer FKIE","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/370131","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/370131","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},{"id":"pmh:oai:pure.mpg.de:item_1323991","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-000F-1776-B","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1965664780","https://openalex.org/W2107048425","https://openalex.org/W2108407691","https://openalex.org/W2114347655","https://openalex.org/W2129833100","https://openalex.org/W2151244813","https://openalex.org/W6676250436"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2039546652","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2138847091"],"abstract_inverted_index":{"We":[0,92],"propose":[1,34],"a":[2,88],"new":[3],"type":[4],"of":[5,19,40,53,65,79,107],"audio":[6],"feature":[7,46],"(HFCC-ENS)":[8],"as":[9,11],"well":[10],"an":[12],"unsupervised":[13],"method":[14,96],"for":[15,61],"detecting":[16],"short":[17],"sequences":[18,78],"spoken":[20,67],"words":[21],"(key-phrases)":[22],"within":[23],"long":[24],"speech":[25,90],"recordings.":[26],"Our":[27],"technical":[28],"contributions":[29],"are":[30],"threefold:":[31],"Firstly,":[32],"we":[33],"to":[35,59],"use":[36],"bandwidth-adapted":[37],"filterbanks":[38],"instead":[39],"classical":[41],"MFCC-style":[42],"filters":[43],"in":[44],"the":[45,50,54,62,66,70,80,94,98,108],"extraction":[47],"step.":[48],"Secondly,":[49],"time":[51],"resolution":[52],"resulting":[55,81],"features":[56,83,85],"is":[57,74],"adapted":[58],"account":[60],"temporal":[63],"characteristics":[64],"phrases.":[68],"Thirdly,":[69],"key-phrase":[71],"detection":[72],"step":[73],"performed":[75],"by":[76],"matching":[77],"HFCC-ENS":[82],"with":[84],"extracted":[86],"from":[87],"target":[89],"recording.":[91],"evaluate":[93],"proposed":[95,109],"using":[97],"German":[99],"Kiel":[100],"Corpus":[101],"and":[102],"furthermore":[103],"investigate":[104],"speech-related":[105],"properties":[106],"feature.":[110]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}
