{"id":"https://openalex.org/W2170681008","doi":"https://doi.org/10.1109/icassp.2012.6289032","title":"Automatic pronunciation prediction for text-to-speech synthesis of dialectal arabic in a speech-to-speech translation system","display_name":"Automatic pronunciation prediction for text-to-speech synthesis of dialectal arabic in a speech-to-speech translation system","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2170681008","doi":"https://doi.org/10.1109/icassp.2012.6289032","mag":"2170681008"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6289032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5090325019","display_name":"Sankaranarayanan Ananthakrishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sankaranarayanan Ananthakrishnan","raw_affiliation_strings":["Raytheon BBN Technologies, Speech, Language and Multimedia Unit, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Speech, Language and Multimedia Unit, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073006801","display_name":"Stavros Tsakalidis","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stavros Tsakalidis","raw_affiliation_strings":["Raytheon BBN Technologies, Speech, Language and Multimedia Unit, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Speech, Language and Multimedia Unit, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107484450","display_name":"Rohit Prasad","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Prasad","raw_affiliation_strings":["Raytheon BBN Technologies, Speech, Language and Multimedia Unit, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Speech, Language and Multimedia Unit, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066184920","display_name":"Prem Natarajan","orcid":"https://orcid.org/0000-0002-4386-6651"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prem Natarajan","raw_affiliation_strings":["Raytheon BBN Technologies, Speech, Language and Multimedia Unit, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Speech, Language and Multimedia Unit, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084986304","display_name":"Aravind Namandi Vembu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Namandi Vembu","raw_affiliation_strings":["Ming-Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ming-Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4957","last_page":"4960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.8709484338760376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8452318906784058},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6614254713058472},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6431272625923157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6373974084854126},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.621446430683136},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5801162719726562},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5142320990562439},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5090343356132507},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47960078716278076},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4444458484649658},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4435604214668274},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.4102938175201416},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16043806076049805}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8709484338760376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8452318906784058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6614254713058472},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6431272625923157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373974084854126},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.621446430683136},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5801162719726562},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5142320990562439},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5090343356132507},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47960078716278076},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4444458484649658},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4435604214668274},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4102938175201416},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16043806076049805},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6289032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W202303397","https://openalex.org/W1773803948","https://openalex.org/W2041349462","https://openalex.org/W2109613320","https://openalex.org/W2153186553","https://openalex.org/W2153653739","https://openalex.org/W6608351394","https://openalex.org/W6637852806","https://openalex.org/W6682169391"],"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/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W39235475","https://openalex.org/W4360995948"],"abstract_inverted_index":{"Text-to-speech":[0],"synthesis":[1],"(TTS)":[2],"is":[3,43,49],"the":[4,8,21,39,46,53,67,72],"final":[5],"stage":[6],"in":[7,20,38,66,95],"speech-tospeech":[9],"(S2S)":[10],"translation":[11,56],"pipeline,":[12],"producing":[13],"an":[14],"audible":[15],"rendition":[16],"of":[17],"translated":[18],"text":[19,62],"target":[22,47],"language.":[23],"TTS":[24],"systems":[25,97],"typically":[26],"rely":[27],"on":[28],"a":[29,85],"lexicon":[30],"to":[31,104],"look":[32],"up":[33],"pronunciations":[34],"for":[35,91,109],"each":[36],"word":[37,124],"input":[40],"text.":[41],"This":[42],"problematic":[44],"when":[45],"language":[48,118],"dialectal":[50,93],"Arabic,":[51],"because":[52],"statistical":[54],"machine":[55],"(SMT)":[57],"system":[58],"usually":[59],"produces":[60],"undiacritized":[61,92],"output.":[63],"Many":[64],"words":[65],"latter":[68],"possess":[69],"multiple":[70],"pronunciations;":[71],"correct":[73],"choice":[74],"must":[75],"be":[76],"inferred":[77],"from":[78,121],"context.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83,113],"present":[84],"weakly":[86],"supervised":[87],"pronunciation":[88,110,129],"prediction":[89,130],"approach":[90],"Arabic":[94],"S2S":[96],"that":[98,115],"leverages":[99],"automatic":[100,123,128],"speech":[101],"recognition":[102],"(ASR)":[103],"obtain":[105],"parallel":[106],"training":[107],"data":[108],"prediction.":[111],"Additionally,":[112],"show":[114],"incorporating":[116],"source":[117],"features":[119],"derived":[120],"SMT-generated":[122],"alignment":[125],"further":[126],"improves":[127],"accuracy.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}