{"id":"https://openalex.org/W1519339192","doi":"https://doi.org/10.21437/interspeech.2013-767","title":"Combining perceptually-motivated spectral shaping with loudness and duration modification for intelligibility enhancement of HMM-based synthetic speech in noise","display_name":"Combining perceptually-motivated spectral shaping with loudness and duration modification for intelligibility enhancement of HMM-based synthetic speech in noise","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W1519339192","doi":"https://doi.org/10.21437/interspeech.2013-767","mag":"1519339192"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-767","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/b741f0e2-2f7d-4c4f-9d19-b9793645478a","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["School of Philosophy Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"113","issue":"76","first_page":"3567","last_page":"3571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9988999962806702,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8120236396789551},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.7351322174072266},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6997982263565063},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.513892650604248},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5083262324333191},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43790942430496216},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4321029484272003},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.3401980400085449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15944987535476685},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15291497111320496}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8120236396789551},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.7351322174072266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6997982263565063},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.513892650604248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5083262324333191},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43790942430496216},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4321029484272003},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3401980400085449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15944987535476685},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15291497111320496},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2013-767","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/b741f0e2-2f7d-4c4f-9d19-b9793645478a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b741f0e2-2f7d-4c4f-9d19-b9793645478a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini-Botinhao, C, Yamagishi, J, King, S & Stylianou, Y 2013, Combining perceptually-motivated spectral shaping with loudness and duration modification for intelligibility enhancement of HMM-based synthetic speech in noise. in Interspeech 2013. < http://www.isca-speech.org/archive/interspeech_2013/i13_3567.html >","raw_type":"contributionToPeriodical"},{"id":"mag:1519339192","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/files/14934475/Combining_perceptually_motivated_spectral_shaping.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S2764744134","display_name":"IEICE technical report. Speech","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEICE technical report. Speech","raw_type":null}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/b741f0e2-2f7d-4c4f-9d19-b9793645478a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b741f0e2-2f7d-4c4f-9d19-b9793645478a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini-Botinhao, C, Yamagishi, J, King, S & Stylianou, Y 2013, Combining perceptually-motivated spectral shaping with loudness and duration modification for intelligibility enhancement of HMM-based synthetic speech in noise. in Interspeech 2013. < http://www.isca-speech.org/archive/interspeech_2013/i13_3567.html >","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W65497148","https://openalex.org/W133559434","https://openalex.org/W1128417033","https://openalex.org/W1588479472","https://openalex.org/W1666286690","https://openalex.org/W1978814037","https://openalex.org/W1980303314","https://openalex.org/W2000513720","https://openalex.org/W2004826498","https://openalex.org/W2005709450","https://openalex.org/W2026024822","https://openalex.org/W2049686551","https://openalex.org/W2075076415","https://openalex.org/W2098930980","https://openalex.org/W2103397742","https://openalex.org/W2118258949","https://openalex.org/W2129387557","https://openalex.org/W2145247325","https://openalex.org/W2149948223","https://openalex.org/W2153914468","https://openalex.org/W2163010125","https://openalex.org/W2171878011","https://openalex.org/W2327204196","https://openalex.org/W2394668095","https://openalex.org/W2404548911"],"related_works":["https://openalex.org/W2403280443","https://openalex.org/W2005709450","https://openalex.org/W2574278440","https://openalex.org/W2019043174","https://openalex.org/W1731717999","https://openalex.org/W1986772939","https://openalex.org/W2748191214","https://openalex.org/W1716865208","https://openalex.org/W2738829087","https://openalex.org/W2542497601","https://openalex.org/W2051593625","https://openalex.org/W3148935696","https://openalex.org/W2602037738","https://openalex.org/W3048908020","https://openalex.org/W1988723164","https://openalex.org/W3035123403","https://openalex.org/W2903592149","https://openalex.org/W2056806152","https://openalex.org/W3010948851","https://openalex.org/W2542098180"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3],"entry":[4],"to":[5,33,52,64],"a":[6,18,23,37],"speech-in-noise":[7],"intelligibility":[8,61],"enhancement":[9,26],"evaluation:":[10],"the":[11,43,91,95],"Hurricane":[12],"Challenge.":[13],"The":[14],"system":[15],"consists":[16],"of":[17,25,29,98],"Text-To-Speech":[19],"voice":[20],"manipulated":[21],"through":[22],"combination":[24],"strategies,":[27],"each":[28],"which":[30,99],"is":[31],"known":[32],"be":[34],"individually":[35],"successful:":[36],"perceptually-motivated":[38],"spectral":[39,92],"shaper":[40,93],"based":[41],"on":[42],"Glimpse":[44],"Proportion":[45],"measure,":[46],"dynamic":[47],"range":[48],"compression,":[49],"and":[50,55,73,84,94,114,125],"adaptation":[51],"Lombard":[53],"excitation":[54,115],"duration":[56],"patterns.":[57],"We":[58],"achieved":[59],"substantial":[60],"improvements":[62],"relative":[63],"unmodified":[65],"synthetic":[66],"speech:":[67],"4.9":[68],"dB":[69,75],"in":[70,76,121],"competing":[71,127],"speaker":[72,128],"4.1":[74],"speech-shaped":[77,111],"noise.":[78,112,129],"An":[79],"analysis":[80],"conducted":[81],"across":[82],"this":[83],"other":[85],"two":[86],"similar":[87],"evaluations":[88],"shows":[89],"that":[90],"compressor":[96],"(both":[97],"are":[100,118],"loudness":[101],"boosters)":[102],"contribute":[103],"most":[104],"under":[105],"higher":[106],"SNR":[107,123],"conditions,":[108,124],"particularly":[109],"for":[110,126],"Duration":[113],"Lombard-adapted":[116],"changes":[117],"more":[119],"beneficial":[120],"lower":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}