{"id":"https://openalex.org/W2406189128","doi":"https://doi.org/10.21437/interspeech.2011-124","title":"Uniform speech parameterization for multi-form segment synthesis","display_name":"Uniform speech parameterization for multi-form segment synthesis","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2406189128","doi":"https://doi.org/10.21437/interspeech.2011-124","mag":"2406189128"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5029658066","display_name":"A. S. Sorin","orcid":"https://orcid.org/0000-0002-9775-2115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Sorin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035109881","display_name":"Slava Shechtman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Slava Shechtman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001028439","display_name":"Vincent Pollet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Pollet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1982,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89962368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"337","last_page":"340"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.996999979019165,"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/waveform","display_name":"Waveform","score":0.8388724327087402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7672103643417358},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7118532657623291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6113131046295166},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5674375891685486},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5508105158805847},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5032889246940613},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.41582542657852173},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.358416885137558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3209100365638733},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06292283535003662}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.8388724327087402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7672103643417358},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7118532657623291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6113131046295166},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5674375891685486},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5508105158805847},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5032889246940613},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.41582542657852173},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.358416885137558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3209100365638733},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06292283535003662},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W111544860","https://openalex.org/W148624016","https://openalex.org/W2103783707","https://openalex.org/W2150658333","https://openalex.org/W2155433314","https://openalex.org/W3142087749"],"related_works":["https://openalex.org/W2100203012","https://openalex.org/W2353790262","https://openalex.org/W2368338897","https://openalex.org/W2893674991","https://openalex.org/W2371805284","https://openalex.org/W2140099343","https://openalex.org/W2039489009","https://openalex.org/W1494715773","https://openalex.org/W2053531689","https://openalex.org/W1842536210"],"abstract_inverted_index":{"In":[0],"multi-form":[1,29,59],"segment":[2,60],"synthesis":[3,61],"speech":[4,9,20,25,37,46],"is":[5,84],"constructed":[6],"by":[7],"sequencing":[8],"segments":[10,30,52,55,83],"of":[11,19],"different":[12],"nature:":[13],"model":[14,51,82,96],"segments,":[15,23],"i.e.":[16,24],"mathematical":[17],"abstractions":[18],"and":[21,53,68,93,97],"template":[22,98],"waveform":[26,54],"fragments.":[27],"These":[28],"can":[31],"have":[32],"shared,":[33],"layered":[34],"or":[35],"alternate":[36],"parameterization":[38,47],"schemes.":[39],"This":[40],"paper":[41],"introduces":[42],"an":[43],"advanced":[44],"uniform":[45],"scheme":[48],"for":[49,81],"statistical":[50],"employed":[56],"in":[57,91],"our":[58],"system.":[62],"Mel-Regularized":[63],"Cepstrum":[64],"derived":[65],"from":[66],"amplitude":[67],"phase":[69],"spectra":[70],"forms":[71],"its":[72],"basic":[73],"framework.":[74],"Furthermore,":[75],"a":[76],"new":[77],"adaptive":[78],"enhancement":[79],"technique":[80],"presented":[85],"that":[86],"reduces":[87],"the":[88],"perceived":[89],"gap":[90],"quality":[92],"similarity":[94],"between":[95],"segments.":[99]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}