{"id":"https://openalex.org/W2182963628","doi":"https://doi.org/10.21437/interspeech.2013-465","title":"An efficient method to estimate pronunciation from multiple utterances","display_name":"An efficient method to estimate pronunciation from multiple utterances","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2182963628","doi":"https://doi.org/10.21437/interspeech.2013-465","mag":"2182963628"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-465","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5067551398","display_name":"Tofigh Naghibi","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Tofigh Naghibi","raw_affiliation_strings":["ETH Z\u00fcrich"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020460474","display_name":"Sarah Hoffmann","orcid":"https://orcid.org/0000-0001-9549-2594"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sarah Hoffmann","raw_affiliation_strings":["ETH Z\u00fcrich"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111975528","display_name":"Beat Pfister","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Beat Pfister","raw_affiliation_strings":["ETH Z\u00fcrich"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067551398"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":1.4427,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8658299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1951","last_page":"1955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.998199999332428,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9955000281333923,"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":0.9922000169754028,"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/soft-output-viterbi-algorithm","display_name":"Soft output Viterbi algorithm","score":0.8839281797409058},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8836274743080139},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.868823766708374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8209618330001831},{"id":"https://openalex.org/keywords/iterative-viterbi-decoding","display_name":"Iterative Viterbi decoding","score":0.6384551525115967},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.6085742712020874},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6055965423583984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5309953689575195},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5198403000831604},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.519307553768158},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5144315361976624},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4516368508338928},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4229554235935211},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3263421058654785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1415114402770996},{"id":"https://openalex.org/keywords/sequential-decoding","display_name":"Sequential decoding","score":0.1414952278137207},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08555775880813599}],"concepts":[{"id":"https://openalex.org/C130319729","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Soft output Viterbi algorithm","level":5,"score":0.8839281797409058},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8836274743080139},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.868823766708374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209618330001831},{"id":"https://openalex.org/C113638808","wikidata":"https://www.wikidata.org/wiki/Q6094410","display_name":"Iterative Viterbi decoding","level":5,"score":0.6384551525115967},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.6085742712020874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6055965423583984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5309953689575195},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5198403000831604},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.519307553768158},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5144315361976624},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4516368508338928},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4229554235935211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3263421058654785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1415114402770996},{"id":"https://openalex.org/C193969084","wikidata":"https://www.wikidata.org/wiki/Q7452500","display_name":"Sequential decoding","level":4,"score":0.1414952278137207},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08555775880813599},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-465","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W943204654","https://openalex.org/W1553004968","https://openalex.org/W1904457459","https://openalex.org/W2025196727","https://openalex.org/W2052998753","https://openalex.org/W2107988889","https://openalex.org/W2130658921","https://openalex.org/W2137919556","https://openalex.org/W2144561722","https://openalex.org/W2146603315","https://openalex.org/W2148450265","https://openalex.org/W2167655920","https://openalex.org/W2619993508","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W2143297499","https://openalex.org/W3096277017","https://openalex.org/W1915619113","https://openalex.org/W2544568790","https://openalex.org/W2790444905","https://openalex.org/W4232476001","https://openalex.org/W1879414379","https://openalex.org/W2783469447","https://openalex.org/W2073817053","https://openalex.org/W2146383045"],"abstract_inverted_index":{"Given":[0],"K":[1],"utterances":[2,47,77],"of":[3,9,17,46,51],"a":[4,7,15],"word":[5,33],"and":[6,100],"set":[8],"sub-word":[10],"units":[11],"one":[12],"may":[13],"need":[14],"generalization":[16],"the":[18,44,49,52,69,75,80],"conventional":[19],"one-dimensional":[20],"Viterbi":[21,54,71],"algorithm":[22,55,67],"to":[23,29,78,84],"jointly":[24],"decode":[25],"them":[26],"in":[27,92],"order":[28],"derive":[30],"their":[31],"underlying":[32],"model":[34],"(pronunciation).":[35],"This":[36],"extension":[37],"is":[38],"called":[39],"k-dimensional":[40,53,70],"Viterbi.":[41],"However,":[42],"as":[43,97],"number":[45],"increases,":[48],"complexity":[50],"exponentially":[56],"increases":[57],"causing":[58],"prohibitive":[59],"computational":[60],"burden.":[61],"Here,":[62],"we":[63],"propose":[64],"an":[65],"approximation":[66],"for":[68],"which":[72],"efficiently":[73],"uses":[74],"available":[76],"estimate":[79],"pronunciation.":[81],"In":[82],"addition":[83],"automatic":[85],"dictionary":[86],"generation,":[87],"it":[88],"can":[89],"be":[90],"used":[91],"computationally":[93],"expensive":[94],"applications":[95],"such":[96],"lexicon-free":[98],"training":[99],"joint":[101,107],"pattern":[102],"alignment.":[103],"Index":[104],"Terms:":[105],"pronunciation,":[106],"decoding,":[108],"k-dimensional,":[109],"viterbi":[110]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}