{"id":"https://openalex.org/W2153750031","doi":"https://doi.org/10.1109/icassp.2010.5495546","title":"An autoencoder neural-network based low-dimensionality approach to excitation modeling for HMM-based text-to-speech","display_name":"An autoencoder neural-network based low-dimensionality approach to excitation modeling for HMM-based text-to-speech","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2153750031","doi":"https://doi.org/10.1109/icassp.2010.5495546","mag":"2153750031"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 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/A5080301608","display_name":"Srikanth Vishnubhotla","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Srikanth Vishnubhotla","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003690515","display_name":"Raul Castro Fernandez","orcid":"https://orcid.org/0000-0001-7675-6080"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raul Fernandez","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080301608"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.9021,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.81502873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"4614","last_page":"4617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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/T11309","display_name":"Music and Audio Processing","score":0.9922999739646912,"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/speech-recognition","display_name":"Speech recognition","score":0.7400709390640259},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7034985423088074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6866748332977295},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6605474948883057},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5600425601005554},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5358890891075134},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.5079174637794495},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5074552893638611},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4784691035747528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44102662801742554},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.43535661697387695},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.420634001493454},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39642706513404846},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37443703413009644},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12614557147026062}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7400709390640259},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7034985423088074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6866748332977295},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6605474948883057},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5600425601005554},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5358890891075134},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.5079174637794495},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5074552893638611},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4784691035747528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44102662801742554},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.43535661697387695},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.420634001493454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39642706513404846},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37443703413009644},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12614557147026062},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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.2010.5495546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W63768818","https://openalex.org/W66838807","https://openalex.org/W92302539","https://openalex.org/W1514941256","https://openalex.org/W1600722501","https://openalex.org/W1756939916","https://openalex.org/W2100495367","https://openalex.org/W2149572519","https://openalex.org/W2157273572","https://openalex.org/W6602604268","https://openalex.org/W6630796692","https://openalex.org/W6637893649","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2363056088","https://openalex.org/W2020989338","https://openalex.org/W2365133740","https://openalex.org/W2147126679","https://openalex.org/W2598586350","https://openalex.org/W1979693044","https://openalex.org/W4361794452","https://openalex.org/W1999835922","https://openalex.org/W2186020725","https://openalex.org/W2145696007"],"abstract_inverted_index":{"HMM-TTS":[0],"synthesis":[1],"is":[2],"a":[3,53,61,68,79],"popular":[4],"approach":[5],"toward":[6],"flexible,":[7],"low-footprint,":[8],"data":[9],"driven":[10],"systems":[11,26],"that":[12,41,85],"produce":[13],"highly":[14],"intelligible":[15],"speech.":[16],"In":[17],"spite":[18],"of":[19,46,64,90],"these":[20,25],"strengths,":[21],"speech":[22,89,98],"generated":[23],"by":[24],"exhibit":[27],"some":[28],"degradation":[29],"in":[30,36],"quality,":[31],"attributable":[32],"to":[33,95],"an":[34,73],"inadequacy":[35],"modeling":[37,57],"the":[38,43,47,58,101],"excitation":[39,59],"signal":[40],"drives":[42],"parametric":[44],"models":[45],"vocal":[48],"tract.":[49],"This":[50],"paper":[51],"proposes":[52],"novel":[54],"method":[55],"for":[56],"as":[60],"low-dimensional":[62],"set":[63],"coefficients,":[65],"based":[66],"on":[67],"non-linear":[69],"map":[70],"learned":[71],"through":[72],"autoencoder.":[74],"Through":[75],"analysis-and-resynthesis":[76],"experiments,":[77],"and":[78],"formal":[80],"listening":[81],"test,":[82],"we":[83],"show":[84],"this":[86],"model":[87],"produces":[88],"higher":[91],"perceptual":[92],"quality":[93],"compared":[94],"conventional":[96],"pulse-excited":[97],"signals":[99],"at":[100],"p":[102],"<;":[103],"0.01":[104],"significance":[105],"level.":[106]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}