{"id":"https://openalex.org/W289035419","doi":"https://doi.org/10.21437/interspeech.2010-182","title":"Improved modelling of speech dynamics using non-linear formant trajectories for HMM-based speech synthesis","display_name":"Improved modelling of speech dynamics using non-linear formant trajectories for HMM-based speech synthesis","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W289035419","doi":"https://doi.org/10.21437/interspeech.2010-182","mag":"289035419"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-182","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5007918444","display_name":"Hongwei Hu","orcid":"https://orcid.org/0000-0003-1284-1328"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hongwei Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079477816","display_name":"Martin Russell","orcid":"https://orcid.org/0000-0002-8324-4961"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin J. Russell","raw_affiliation_strings":["University of Birmingham, Birmingham, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Birmingham, Birmingham, United Kingdom","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007918444"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.929,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79134149,"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":"821","last_page":"824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9786999821662903,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.8508697748184204},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7358525991439819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722364068031311},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7052700519561768},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5605493783950806},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5316781401634216},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49109554290771484},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.4259134829044342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3362169563770294},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1914260983467102}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8508697748184204},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7358525991439819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722364068031311},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7052700519561768},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5605493783950806},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5316781401634216},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49109554290771484},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.4259134829044342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3362169563770294},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1914260983467102},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-182","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/efec4461-0198-45a0-99ab-42eed60578d6","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/portal/en/publications/improved-modelling-of-speech-dynamics-using-nonlinear-formant-trajectories-for-hmmbased-speech-synthesis(efec4461-0198-45a0-99ab-42eed60578d6).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hu, H & Russell, M 2010, 'Improved modelling of speech dynamics using non-linear formant trajectories for HMM-based speech synthesis', Paper presented at 11th Annual Conference of the International Speech Communication Association 2010 (Interspeech 2010), Vols 1-4, 1/01/10 pp. 821-824.","raw_type":"conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W314395536","https://openalex.org/W1594223010","https://openalex.org/W2007954099","https://openalex.org/W2014647161","https://openalex.org/W2103764823","https://openalex.org/W2118825896","https://openalex.org/W2154920538"],"related_works":["https://openalex.org/W19748186","https://openalex.org/W2611973037","https://openalex.org/W2131825398","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W165161405","https://openalex.org/W2019253074","https://openalex.org/W1969351994","https://openalex.org/W2164147372"],"abstract_inverted_index":null,"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}