{"id":"https://openalex.org/W10731371","doi":"https://doi.org/10.21437/icslp.1998-603","title":"A recursive algorithm for the forced alignment of very long audio segments","display_name":"A recursive algorithm for the forced alignment of very long audio segments","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W10731371","doi":"https://doi.org/10.21437/icslp.1998-603","mag":"10731371"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-603","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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/A5103874391","display_name":"Pedro J. Moreno","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro J. Moreno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097688309","display_name":"Chris Joerg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Joerg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039142030","display_name":"Jean-Manuel Van Thong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Manuel Van Thong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018914598","display_name":"Oren Glickman","orcid":"https://orcid.org/0009-0000-5158-7372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oren Glickman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":140,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 0068","last_page":"0"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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":0.9986000061035156,"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":0.7115158438682556},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4196653962135315},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35383105278015137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7115158438682556},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4196653962135315},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35383105278015137}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.1998-603","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.649.6346","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.649.6346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://oren.glickman.com/publications/moreno_et_al_icslp98.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W84827648","https://openalex.org/W151797875","https://openalex.org/W203760253","https://openalex.org/W2013196554","https://openalex.org/W2120358855"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2317200988","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829"],"abstract_inverted_index":{"In":[0],"this":[1,35,49],"paper":[2],"we":[3],"address":[4],"the":[5,54,84,134,204,208],"problem":[6,36,57,63],"of":[7,48,115,174,207],"aligning":[8],"very":[9],"long":[10],"(of-ten":[11],"more":[12,170],"than":[13,171],"one":[14,197],"hour)":[15],"audio":[16,88,98,136,175,187,209],"files":[17],"to":[18,33,52,76,198],"their":[19],"corresponding":[20],"textual":[21],"transcripts":[22],"in":[23,83,161,195],"an":[24,29],"effective":[25],"manner.":[26],"We":[27,90,105,129],"present":[28],"efficient":[30],"recur-sive":[31],"technique":[32],"solve":[34],"that":[37],"works":[38],"well":[39],"even":[40],"on":[41,94,110,203],"noisy":[42],"speech":[43,61,111,121,125,192],"signals.":[44],"The":[45,72,189],"key":[46],"idea":[47],"algorithm":[50,73,157],"is":[51,74],"turn":[53],"forced":[55],"alignment":[56],"into":[58],"a":[59,65,95,113,148],"recursive":[60],"recognition":[62],"with":[64,141],"gradually":[66],"restricting":[67],"dictionary":[68],"and":[69,79,102,124,184],"language":[70],"model.":[71],"tolerant":[75],"acoustic":[77,117,205],"noise":[78,144],"errors":[80],"or":[81,87,145],"gaps":[82],"text":[85],"transcript":[86],"tracks.":[89],"report":[91,131],"experimental":[92],"results":[93],"3":[96],"hour":[97],"file":[99],"containing":[100],"TV":[101],"radio":[103],"broadcasts.":[104],"will":[106],"show":[107],"accurate":[108],"alignments":[109],"under":[112],"variety":[114],"real":[116],"conditions":[118,206],"such":[119,153,179],"as":[120,154,180],"over":[122,126],"music":[123],"telephone":[127],"lines.":[128],"also":[130],"re-sults":[132],"when":[133],"same":[135],"stream":[137],"has":[138,158,168],"been":[139,159],"corrupted":[140],"white":[142],"additive":[143],"compressed":[146],"using":[147],"popular":[149],"web":[150,186],"encoding":[151],"for-mat":[152],"RealAudio.":[155],"This":[156],"used":[160],"our":[162],"internal":[163],"multimedia":[164],"indexing":[165],"project.":[166],"It":[167],"processed":[169],"200":[172],"hours":[173],"from":[176],"var-ied":[177],"sources,":[178],"WGBH":[181],"NOVA":[182],"documentaries":[183],"NPR":[185],"files.":[188],"system":[190],"aligns":[191],"media":[193],"content":[194],"about":[196],"five":[199],"times":[200],"realtime,":[201],"depending":[202],"signal.":[210],"1.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}