{"id":"https://openalex.org/W2118258949","doi":"https://doi.org/10.1109/icassp.2005.1415101","title":"Improving the Understandability of Speech Synthesis by Modeling Speech in Noise","display_name":"Improving the Understandability of Speech Synthesis by Modeling Speech in Noise","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2118258949","doi":"https://doi.org/10.1109/icassp.2005.1415101","mag":"2118258949"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 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/A5058756331","display_name":"Brian Langner","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"B. Langner","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A.W. Black","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058756331"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.6361,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.68070804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"265","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9944999814033508,"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/T12031","display_name":"Speech and dialogue systems","score":0.9800000190734863,"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/computer-science","display_name":"Computer science","score":0.7467384338378906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7112753987312317},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6957540512084961},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6668267250061035},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5010693073272705},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4528128504753113},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.41314923763275146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3372892141342163},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25388503074645996},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08007797598838806}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7467384338378906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7112753987312317},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6957540512084961},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6668267250061035},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5010693073272705},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4528128504753113},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.41314923763275146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3372892141342163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25388503074645996},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08007797598838806},{"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:10.1109/icassp.2005.1415101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W23142961","https://openalex.org/W97509088","https://openalex.org/W140742084","https://openalex.org/W1496801689","https://openalex.org/W1516479813","https://openalex.org/W1524333034","https://openalex.org/W2084609288","https://openalex.org/W6600922454","https://openalex.org/W6605689486"],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2275432853","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W127416991","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W197907117"],"abstract_inverted_index":{"Although":[0],"the":[1,10,24,50,61,64,76,104],"quality":[2,26],"of":[3,35,52,78,91,106,109],"synthetic":[4,36,79,111],"speech":[5,20,37,39,43,53,80,93,99],"has":[6],"increased":[7],"dramatically":[8],"in":[9,40,44,49,68,81,94,98,115],"past":[11],"several":[12,110],"years,":[13],"many":[14],"people":[15,58],"still":[16],"have":[17],"difficulty":[18],"understanding":[19],"produced":[21],"by":[22,57],"even":[23],"highest":[25],"synthesizers.":[27],"We":[28,72],"describe":[29],"an":[30,107],"approach":[31],"to":[32,59,63],"improve":[33,60],"understandability":[34,62],"using":[38],"noise.":[41],"Natural":[42],"noise":[45,95],"is":[46,55],"a":[47],"change":[48],"style":[51],"that":[54,74,113],"used":[56],"listener":[65],"when":[66],"speaking":[67],"poor":[69],"channel":[70],"conditions.":[71],"show":[73],"altering":[75],"presentation":[77],"similar":[82],"ways":[83],"also":[84],"improves":[85],"understandability.":[86],"Further,":[87],"we":[88],"discuss":[89],"methods":[90],"obtaining":[92],"for":[96],"use":[97],"synthesis,":[100],"as":[101,103],"well":[102],"results":[105],"evaluation":[108],"voices":[112],"\"speak":[114],"noise\".":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}