{"id":"https://openalex.org/W2096270777","doi":"https://doi.org/10.1109/icassp.2009.4960554","title":"Audio segmentation for speech recognition using segment features","display_name":"Audio segmentation for speech recognition using segment features","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2096270777","doi":"https://doi.org/10.1109/icassp.2009.4960554","mag":"2096270777"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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/A5050133412","display_name":"David Rybach","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"David Rybach","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Germany","Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Germany#TAB#","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084597617","display_name":"Christian Gollan","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Gollan","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Germany","Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Germany#TAB#","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schluter","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Germany","Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Germany#TAB#","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Germany","Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Germany#TAB#","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050133412"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":1.4272,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.80814378,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4197","last_page":"4200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/segmentation","display_name":"Segmentation","score":0.8636566400527954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.804047167301178},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6740917563438416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6565883755683899},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5233197212219238},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5190235376358032},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.47745922207832336},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47689202427864075},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4697941541671753},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4614921808242798},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.43355000019073486},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4280986785888672},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.39276322722435},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.18507036566734314}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8636566400527954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804047167301178},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6740917563438416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6565883755683899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5233197212219238},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5190235376358032},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.47745922207832336},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47689202427864075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4697941541671753},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4614921808242798},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.43355000019073486},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4280986785888672},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.39276322722435},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.18507036566734314},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2009.4960554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.163.7527","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.163.7527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/publications/download/594/Audio Segmentation for Speech Recognition using Segment Features.pdf","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:125766","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/125766","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"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, 2009 : ICASSP 2009 ; 19 - 24 April 2009, Taipei International Convention Center, Taipei, Taiwan ; proceedings / sponsored by the Institute of Electrical and Electronics Engineers Signal Processing Society. - Vol. 7<br/>IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2009, Taipei, Taiwan, 2009-04-19 - 2009-04-24","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W2016243284","https://openalex.org/W2063415950","https://openalex.org/W2116656681","https://openalex.org/W2140537255","https://openalex.org/W2159937480","https://openalex.org/W2163238203","https://openalex.org/W2168175751","https://openalex.org/W6628802092","https://openalex.org/W6628911050","https://openalex.org/W7009185688"],"related_works":["https://openalex.org/W4225315139","https://openalex.org/W2063862874","https://openalex.org/W2154415461","https://openalex.org/W1923241916","https://openalex.org/W1546240199","https://openalex.org/W4292261062","https://openalex.org/W4385881881","https://openalex.org/W2151365363","https://openalex.org/W2798852438","https://openalex.org/W642007152"],"abstract_inverted_index":{"Audio":[0],"segmentation":[1,34,47,73,86],"is":[2,42,81],"an":[3,49],"essential":[4],"preprocessing":[5],"step":[6],"in":[7,52,75],"several":[8],"audio":[9,50],"processing":[10],"applications":[11],"with":[12],"a":[13,23,53,57,59,84],"significant":[14],"impact":[15],"e.g.":[16],"on":[17],"speech":[18,78],"recognition":[19,79],"performance.":[20],"We":[21],"introduce":[22],"novel":[24],"framework":[25],"which":[26],"combines":[27],"the":[28,46],"advantages":[29],"of":[30,48,64,77,88],"different":[31],"well":[32],"known":[33],"methods.":[35],"An":[36],"automatically":[37],"estimated":[38],"log-linear":[39],"segment":[40],"model":[41],"used":[43],"to":[44,71],"determine":[45],"stream":[51],"holistic":[54],"way":[55],"by":[56],"maximum":[58],"posteriori":[60],"decoding":[61],"strategy,":[62],"instead":[63],"classifying":[65],"change":[66],"points":[67],"locally.":[68],"A":[69],"comparison":[70],"other":[72],"techniques":[74],"terms":[76],"performance":[80],"presented,":[82],"showing":[83],"promising":[85],"quality":[87],"our":[89],"approach.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}