{"id":"https://openalex.org/W163031146","doi":"https://doi.org/10.21437/interspeech.2006-405","title":"From pre-recorded prompts to corporate voices: on the migration of interactive voice response applications","display_name":"From pre-recorded prompts to corporate voices: on the migration of interactive voice response applications","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W163031146","doi":"https://doi.org/10.21437/interspeech.2006-405","mag":"163031146"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-405","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5015413878","display_name":"Volker Fischer","orcid":"https://orcid.org/0000-0001-5437-4030"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"V. Fischer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074068808","display_name":"Siegfried Kunzmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Kunzmann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01391759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 1042","last_page":"Wed3BuP.10"},"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":0.9983999729156494,"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/T12031","display_name":"Speech and dialogue systems","score":0.9983999729156494,"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":0.7852261066436768},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7040876150131226},{"id":"https://openalex.org/keywords/interactive-voice-response","display_name":"Interactive voice response","score":0.7036317586898804},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6147037148475647},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5600632429122925},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5047506093978882},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46669867634773254},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46534642577171326},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.4533889889717102},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39980387687683105},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37999609112739563},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3283069133758545},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10813918709754944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852261066436768},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7040876150131226},{"id":"https://openalex.org/C2777858628","wikidata":"https://www.wikidata.org/wiki/Q1111837","display_name":"Interactive voice response","level":2,"score":0.7036317586898804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6147037148475647},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5600632429122925},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5047506093978882},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46669867634773254},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46534642577171326},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.4533889889717102},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39980387687683105},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37999609112739563},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3283069133758545},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10813918709754944},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2006-405","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W63768818","https://openalex.org/W75668230","https://openalex.org/W91484551","https://openalex.org/W1574964715","https://openalex.org/W1577446345","https://openalex.org/W2033010331","https://openalex.org/W2110589840","https://openalex.org/W2140011577","https://openalex.org/W2150658333","https://openalex.org/W2396600922","https://openalex.org/W2543977149"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W642007152","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W1909292483","https://openalex.org/W2052688117","https://openalex.org/W596245619"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3],"efforts":[4],"towards":[5],"the":[6,58,87,90,116,131,136],"creation":[7,59],"of":[8,46,60,89],"corporate":[9,62],"synthetic":[10],"voices":[11,63,118,122],"from":[12,68,77,125],"low":[13],"quality":[14],"speech":[15,66],"data,":[16,127],"as":[17,135],"it":[18,94],"can":[19],"typically":[20],"be":[21],"found":[22],"on":[23,36,42],"many":[24],"Interactive":[25],"Voice":[26],"Response":[27],"(IVR)":[28],"units.":[29],"In":[30],"doing":[31],"so,":[32],"we":[33,54],"first":[34],"touch":[35],"several":[37],"normalization":[38],"techniques":[39],"that":[40,100,115],"aim":[41],"a":[43,47,96,107],"better":[44],"support":[45],"highly":[48],"automated":[49],"voice":[50],"construction":[51],"process.":[52],"Subsequently,":[53],"describe":[55],"methods":[56],"for":[57],"enriched":[61,117],"which":[64,85],"integrate":[65],"recordings":[67],"different":[69],"speakers":[70],"in":[71,104],"order":[72],"to":[73,95],"overcome":[74],"problems":[75],"arising":[76],"limited":[78],"domain":[79],"training":[80],"data.":[81],"Experiments":[82],"are":[83],"described":[84],"demonstrate":[86],"feasibility":[88],"approach":[91],"by":[92],"comparing":[93],"less":[97],"flexible":[98],"solution":[99],"uses":[101],"pre-recorded":[102,137],"prompts":[103,138],"combination":[105],"with":[106],"large":[108],"footprint":[109],"standard":[110],"concatenative":[111],"synthesizer.":[112],"Results":[113],"show":[114],"clearly":[119],"outperform":[120],"those":[121],"build":[123],"solely":[124],"IVR":[126],"while":[128],"achieving":[129],"almost":[130],"same":[132],"overall":[133],"rating":[134],"solution.":[139]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
