{"id":"https://openalex.org/W1967924372","doi":"https://doi.org/10.1109/icassp.2013.6639241","title":"Weak top-down constraints for unsupervised acoustic model training","display_name":"Weak top-down constraints for unsupervised acoustic model training","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1967924372","doi":"https://doi.org/10.1109/icassp.2013.6639241","mag":"1967924372"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 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/A5103622427","display_name":"Aren Jansen","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aren Jansen","raw_affiliation_strings":["Human Language Technology Center of Excellence, Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["Human Language Technology Center of Excellence, Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":["Human Language Technology Center of Excellence, Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103622427"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":11.3709,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.98241732,"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":"8091","last_page":"8095"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/pronunciation","display_name":"Pronunciation","score":0.79560786485672},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7933135032653809},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5939501523971558},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5830100178718567},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.5813666582107544},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5239707827568054},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.48058414459228516},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.4571944773197174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4103611707687378},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33091723918914795},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20268014073371887},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10675078630447388},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09758713841438293}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.79560786485672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7933135032653809},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5939501523971558},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5830100178718567},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5813666582107544},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5239707827568054},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.48058414459228516},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.4571944773197174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4103611707687378},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33091723918914795},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20268014073371887},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10675078630447388},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09758713841438293},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.640.3809","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.640.3809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/~samuel/pdfs/wk_const.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W66167291","https://openalex.org/W156237177","https://openalex.org/W1539935047","https://openalex.org/W1606268232","https://openalex.org/W2057007397","https://openalex.org/W2062914951","https://openalex.org/W2079460648","https://openalex.org/W2090861223","https://openalex.org/W2100768664","https://openalex.org/W2103933358","https://openalex.org/W2114347655","https://openalex.org/W2114478143","https://openalex.org/W2117041980","https://openalex.org/W2121947440","https://openalex.org/W2126203737","https://openalex.org/W2128160875","https://openalex.org/W2399869768","https://openalex.org/W2401464865","https://openalex.org/W2406820985","https://openalex.org/W2407151108","https://openalex.org/W2407964052","https://openalex.org/W3148201686","https://openalex.org/W6602705600","https://openalex.org/W6675022971","https://openalex.org/W6714100551"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W2359469050","https://openalex.org/W1607396156"],"abstract_inverted_index":{"Typical":[0],"supervised":[1],"acoustic":[2,93],"model":[3,116,131],"training":[4,141],"relies":[5],"on":[6],"strong":[7],"top-down":[8,38,125],"constraints":[9,126],"provided":[10],"by":[11,134],"dynamic":[12,88],"programming":[13,89],"alignment":[14,90],"of":[15,37,44,70,72,91,95,103,129],"the":[16,49,68,78,92,96,112],"input":[17],"observations":[18,94],"to":[19,136],"phonetic":[20],"sequences":[21],"derived":[22],"from":[23],"orthographic":[24],"word":[25,74],"transcripts":[26,45],"and":[27,46],"pronunciation":[28],"dictionaries.":[29],"This":[30],"paper":[31],"investigates":[32],"a":[33,87],"much":[34],"weaker":[35],"form":[36,69],"supervision":[39],"for":[40,119],"use":[41],"in":[42,48,67],"place":[43],"dictionaries":[47],"zero":[50],"resource":[51],"setting.":[52],"Our":[53],"proposed":[54],"constraints,":[55],"which":[56],"can":[57],"be":[58],"produced":[59],"using":[60],"recent":[61],"spoken":[62],"term":[63],"discovery":[64],"systems,":[65],"come":[66],"pairs":[71,106],"isolated":[73],"examples":[75],"that":[76,107,111],"share":[77],"same":[79,113],"unknown":[80],"type.":[81],"For":[82],"each":[83,108],"pair,":[84],"we":[85],"perform":[86],"two":[97],"constituent":[98],"examples,":[99],"generating":[100],"an":[101],"inventory":[102],"cross-speaker":[104],"frame":[105],"provide":[109],"evidence":[110],"subword":[114],"unit":[115],"should":[117],"account":[118],"them.":[120],"We":[121],"find":[122],"these":[123],"weak":[124],"are":[127],"capable":[128],"improving":[130],"speaker":[132],"independence":[133],"up":[135],"57%":[137],"relative":[138],"over":[139],"bottom-up":[140],"alone.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}