{"id":"https://openalex.org/W85707815","doi":"https://doi.org/10.21437/interspeech.2006-449","title":"Automatic alignment and error correction of human generated transcripts for long speech recordings","display_name":"Automatic alignment and error correction of human generated transcripts for long speech recordings","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W85707815","doi":"https://doi.org/10.21437/interspeech.2006-449","mag":"85707815"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-449","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5114018312","display_name":"Timothy J. Hazen","orcid":"https://orcid.org/0009-0006-1413-9590"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Timothy J. Hazen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5114018312"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4483,"has_fulltext":false,"cited_by_count":97,"citation_normalized_percentile":{"value":0.96979182,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"paper 1258","last_page":"Wed1CaP.2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8487045764923096},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7351749539375305},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7059810161590576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6849452257156372},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5174508690834045},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4933737814426422},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44083383679389954},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40462300181388855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38108348846435547},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.36618679761886597}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8487045764923096},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7351749539375305},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7059810161590576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6849452257156372},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5174508690834045},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4933737814426422},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44083383679389954},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40462300181388855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38108348846435547},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.36618679761886597},{"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2006-449","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.154.5104","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.5104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sls.csail.mit.edu/sls/publications/2006/IS061258.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4000000059604645,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W1501139663","https://openalex.org/W1515452908","https://openalex.org/W1631260214","https://openalex.org/W1975113979","https://openalex.org/W2037099546","https://openalex.org/W2111732304","https://openalex.org/W2143562645","https://openalex.org/W2159344129","https://openalex.org/W2331071225"],"related_works":["https://openalex.org/W2131156500","https://openalex.org/W2118916824","https://openalex.org/W2157598242","https://openalex.org/W2037564206","https://openalex.org/W1479881079","https://openalex.org/W3159882232","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"examine":[4],"the":[5,35,54,80,97,122,126],"issues":[6],"of":[7,40,68,109],"aligning":[8],"and":[9,38,91,118],"correcting":[10],"approximate":[11,107],"human":[12],"generated":[13,85],"transcripts":[14,84],"for":[15,57,106],"long":[16,110],"audio":[17,27,41,51,111],"files.":[18],"Accurate":[19,43],"time-aligned":[20],"transcriptions":[21,70,108],"help":[22],"provide":[23,64],"easier":[24],"access":[25],"to":[26,116],"materials":[28],"by":[29,86],"aiding":[30],"downstream":[31],"applications":[32],"such":[33],"as":[34],"indexing,":[36],"summarizing":[37],"retrieving":[39],"segments.":[42],"time":[44],"alignments":[45],"are":[46],"also":[47],"necessary":[48],"when":[49],"incorporating":[50],"data":[52,56],"into":[53],"training":[55],"a":[58,102],"speech":[59],"recognizer\u2019s":[60],"acoustic":[61],"model.":[62],"We":[63,99],"some":[65],"initial":[66],"analysis":[67],"manual":[69,83,123],"which":[71,113],"show":[72],"that":[73],"there":[74],"can":[75],"be":[76],"significant":[77],"differences":[78],"between":[79],"\u201capproximate":[81],"\u201d":[82],"typical":[87],"commercial":[88],"transcription":[89,124],"services":[90],"what":[92],"was":[93],"actually":[94],"spoken":[95],"in":[96,121],"recording.":[98],"then":[100],"present":[101],"new":[103],"alignment":[104,127],"approach":[105],"files":[112],"is":[114],"designed":[115],"discover":[117],"correct":[119],"errors":[120],"during":[125],"process.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}