{"id":"https://openalex.org/W343569862","doi":"https://doi.org/10.21437/interspeech.2005-797","title":"Small footprint concatenative text-to-speech synthesis system using complex spectral envelope modeling","display_name":"Small footprint concatenative text-to-speech synthesis system using complex spectral envelope modeling","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W343569862","doi":"https://doi.org/10.21437/interspeech.2005-797","mag":"343569862"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-797","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5103348951","display_name":"Dan Chazan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Chazan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053864983","display_name":"Ron Hoory","orcid":"https://orcid.org/0009-0006-1327-5160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron Hoory","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054462082","display_name":"Zvi Kons","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zvi Kons","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110197506","display_name":"Ariel Sagi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ariel Sagi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035109881","display_name":"Slava Shechtman","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Slava Shechtman","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","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":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6201,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.82612319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2569","last_page":"2572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7344808578491211},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.6481695175170898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6142224669456482},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.5980355143547058},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5742254853248596},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.4701509475708008},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.4482821524143219},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4168701469898224},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0900954008102417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7344808578491211},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.6481695175170898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6142224669456482},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.5980355143547058},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5742254853248596},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.4701509475708008},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.4482821524143219},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4168701469898224},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0900954008102417},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2005-797","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.542.2554","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.542.2554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.ibm.com/haifa/projects/imt/ectts/papers/SpeechModeling_Eurospeech2005.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W148624016","https://openalex.org/W293337345","https://openalex.org/W1493163583","https://openalex.org/W2129082420","https://openalex.org/W2160972557","https://openalex.org/W2164764235"],"related_works":["https://openalex.org/W254868496","https://openalex.org/W2073905179","https://openalex.org/W2928432034","https://openalex.org/W4200277070","https://openalex.org/W1989331194","https://openalex.org/W4300740495","https://openalex.org/W1969398023","https://openalex.org/W2323643941","https://openalex.org/W2619026611","https://openalex.org/W1998822346"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"a":[5,35,80,87],"method":[6,21],"for":[7,74],"speech":[8,42,65],"modeling":[9,45],"and":[10,56,59],"its":[11],"utilization":[12],"in":[13,38,83],"IBM\u2019s":[14],"small":[15],"footprint":[16],"concatenative":[17],"text-to-speech":[18,77],"system.":[19,90],"The":[20,44],"is":[22],"based":[23],"on":[24],"frequency-domain,":[25],"complex":[26],"spectral":[27],"envelope":[28],"modeling,":[29],"where":[30],"the":[31,54,75],"phase":[32,57],"component":[33],"plays":[34],"crucial":[36],"role":[37],"attaining":[39],"high":[40,63],"quality":[41,64],"synthesis.":[43],"scheme":[46],"presented":[47],"enables":[48],"low":[49],"bit":[50],"rate":[51],"compression":[52],"of":[53,62],"amplitude":[55],"information":[58],"low-complexity":[60],"reconstruction":[61],"with":[66],"wide":[67],"range":[68],"pitch":[69],"modification.":[70],"Listening":[71],"tests":[72],"conducted":[73],"overall":[76],"system":[78],"show":[79],"major":[81],"improvement":[82],"MOS,":[84],"compared":[85],"to":[86],"previous,":[88],"MFCC-based,":[89],"1.":[91]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
