{"id":"https://openalex.org/W2105961775","doi":"https://doi.org/10.1109/icassp.2009.4960722","title":"A factor automaton approach for the forced alignment of long speech recordings","display_name":"A factor automaton approach for the forced alignment of long speech recordings","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2105961775","doi":"https://doi.org/10.1109/icassp.2009.4960722","mag":"2105961775"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960722","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":"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":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro J. Moreno","raw_affiliation_strings":["Speech Research Group, Google, Inc., New York, NY, USA","Speech Research Group, Google Inc., 76 Ninth Avenue, New York, 10011, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Group, Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Speech Research Group, Google Inc., 76 Ninth Avenue, New York, 10011, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023967160","display_name":"Christopher Alberti","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Alberti","raw_affiliation_strings":["Speech Research Group, Google, Inc., New York, NY, USA","Speech Research Group, Google Inc., 76 Ninth Avenue, New York, 10011, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Group, Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Speech Research Group, Google Inc., 76 Ninth Avenue, New York, 10011, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4869","last_page":"4872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","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":0.996399998664856,"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/substring","display_name":"Substring","score":0.815723717212677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7764549255371094},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6655483245849609},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.6287135481834412},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5843689441680908},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.5681467056274414},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.4618813693523407},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43715909123420715},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.41203540563583374},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.41127872467041016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3847094178199768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3751089870929718},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32277363538742065},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.18928462266921997},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15203320980072021},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10859307646751404}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.815723717212677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764549255371094},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6655483245849609},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.6287135481834412},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5843689441680908},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.5681467056274414},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4618813693523407},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43715909123420715},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.41203540563583374},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41127872467041016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3847094178199768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3751089870929718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32277363538742065},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.18928462266921997},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15203320980072021},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10859307646751404},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960722","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W60437269","https://openalex.org/W85707815","https://openalex.org/W106647055","https://openalex.org/W1525128434","https://openalex.org/W1582482241","https://openalex.org/W1972770363","https://openalex.org/W1975113979","https://openalex.org/W2074932712","https://openalex.org/W2154104338","https://openalex.org/W2161564256","https://openalex.org/W2183390198","https://openalex.org/W6600436803","https://openalex.org/W6603477829","https://openalex.org/W6604245201"],"related_works":["https://openalex.org/W2141389247","https://openalex.org/W1570166875","https://openalex.org/W2473935755","https://openalex.org/W2250909759","https://openalex.org/W2170798490","https://openalex.org/W2024152506","https://openalex.org/W2532616038","https://openalex.org/W2787311093","https://openalex.org/W155946694","https://openalex.org/W1555968995"],"abstract_inverted_index":{"This":[0,54],"paper":[1,34],"addresses":[2],"the":[3,25,29,37,64],"problem":[4],"of":[5,39],"aligning":[6],"long":[7],"speech":[8],"recordings":[9],"to":[10,27,47,95],"their":[11],"transcripts.":[12,65],"Previous":[13],"work":[14],"has":[15],"focused":[16],"on":[17,24,63],"using":[18],"highly":[19,58],"tuned":[20],"language":[21,60],"models":[22,72],"trained":[23,62],"transcripts":[26],"reduce":[28],"search":[30],"space.":[31],"In":[32],"this":[33],"we":[35],"propose":[36],"use":[38],"a":[40,43,52,57,83,89],"factor":[41],"automaton,":[42],"well":[44],"known":[45],"method":[46],"represent":[48],"all":[49],"substrings":[50],"from":[51],"string.":[53],"automaton":[55],"encodes":[56],"constrained":[59],"model":[61],"We":[66],"show":[67,79],"competitive":[68],"results":[69],"with":[70,88],"n-gram":[71,96],"in":[73],"several":[74],"testing":[75],"scenarios.":[76],"Preliminary":[77],"experiments":[78],"perfect":[80],"alignments":[81],"at":[82],"reduced":[84],"computational":[85],"load":[86],"and":[87],"smaller":[90],"memory":[91],"footprint":[92],"when":[93],"compared":[94],"models.":[97]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}