{"id":"https://openalex.org/W2136419841","doi":"https://doi.org/10.1109/icassp.1984.1172426","title":"A procedure for automatic alignment of phonetic transcriptions with continuous speech","display_name":"A procedure for automatic alignment of phonetic transcriptions with continuous speech","publication_year":2005,"publication_date":"2005-03-24","ids":{"openalex":"https://openalex.org/W2136419841","doi":"https://doi.org/10.1109/icassp.1984.1172426","mag":"2136419841"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1984.1172426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1984.1172426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '84. 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/A5102984697","display_name":"Hong Leung","orcid":"https://orcid.org/0009-0002-5901-0863"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Leung","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109575396","display_name":"Victor W. Zue","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. Zue","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.4645,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.90223637,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":null,"first_page":"73","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9977999925613403,"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":0.7918789386749268},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7531521320343018},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5233135223388672},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47596806287765503},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42891982197761536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4095996618270874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918789386749268},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7531521320343018},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5233135223388672},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47596806287765503},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42891982197761536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4095996618270874}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1984.1172426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1984.1172426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '84. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1486671204","https://openalex.org/W1623080549","https://openalex.org/W1835737061","https://openalex.org/W2073693905","https://openalex.org/W2092234602","https://openalex.org/W2128533005","https://openalex.org/W4400445037"],"related_works":["https://openalex.org/W2794438528","https://openalex.org/W1658560081","https://openalex.org/W2588431733","https://openalex.org/W1480529103","https://openalex.org/W2164147372","https://openalex.org/W2216757598","https://openalex.org/W2102737569","https://openalex.org/W2358020347","https://openalex.org/W2085871660","https://openalex.org/W596245619"],"abstract_inverted_index":{"A":[0,28],"system":[1,65,74,113],"for":[2,49],"automatic":[3,111],"alignment":[4,59,112],"of":[5,47,55,90,100],"phonetic":[6,40,62],"transcriptions":[7],"with":[8,38],"continuous":[9],"speech":[10,15],"has":[11],"been":[12],"developed.":[13],"The":[14,73,123],"signal":[16],"is":[17,118],"first":[18],"segmented":[19],"into":[20,95],"broad":[21,36,43],"classes":[22,37,44],"using":[23],"a":[24,115],"non-parametric":[25],"Pattern":[26],"classifier.":[27],"knowledge-based":[29],"dynamic":[30],"programming":[31],"algorithm":[32],"then":[33],"aligns":[34],"the":[35,39,61,64,91,101,103,106,110],"transcriptions.":[41],"These":[42],"provide":[45],"\"islands":[46],"reliability\"":[48],"more":[50,130],"detailed":[51],"segmentation":[52],"and":[53,70,86,114],"refinement":[54],"boundaries.":[56],"By":[57],"doing":[58],"at":[60],"level,":[63],"can":[66,125],"often":[67],"tolerate":[68],"inter":[69],"intra-speaker":[71],"variability.":[72],"was":[75],"evaluated":[76],"on":[77],"sixty":[78],"sentences":[79],"spoken":[80],"by":[81,109,128],"three":[82],"speakers,":[83],"two":[84],"male":[85],"one":[87,97],"female.":[88],"93%":[89],"segments":[92],"are":[93],"mapped":[94],"only":[96],"phoneme,":[98],"70%":[99],"time":[102],"offset":[104],"between":[105],"boundary":[107],"found":[108],"hand":[116],"transcriber":[117],"less":[119],"than":[120],"10":[121],"ms.":[122],"performance":[124],"be":[126],"improved":[127],"applying":[129],"heuristic":[131],"rules.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}