Utilize este identificador para referenciar este registo: http://hdl.handle.net/10071/15133
Autoria: Hämäläinen, A.
Meinedo, H.
Tjalve, M.
Pellegrini, T.
Trancoso, I.
Dias, M. S.
Data: 2014
Título próprio: Improving speech recognition through automatic selection of age group – specific acoustic models
Volume: 8775
Paginação: 12-23
ISSN: 0302-9743
ISBN: 978-3-319-09761-9
DOI (Digital Object Identifier): 10.1007/978-3-319-09761-9_2
Palavras-chave: Acoustic modelling
Age group classification
Automatic speech recognition
Children
Elderly
Paralinguistic information
Resumo: The acoustic models used by automatic speech recognisers are usually trained with speech collected from young to middle-aged adults. As the characteristics of speech change with age, such acoustic models tend to perform poorly on children’s and elderly people’s speech. In this study, we investigate whether the automatic age group classification of speakers, together with age group –specific acoustic models, could improve automatic speech recognition performance. We train an age group classifier with an accuracy of about 95% and show that using the results of the classifier to select age group –specific acoustic models for children and the elderly leads to considerable gains in automatic speech recognition performance, as compared with using acoustic models trained with young to middle-aged adults’ speech for recognising their speech, as well.
Arbitragem científica: yes
Acesso: Acesso Aberto
Aparece nas coleções:ISTAR-CLI - Capítulos de livros internacionais

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
Improving speech recognition through automatic selection of age group.pdfPós-print261,62 kBAdobe PDFVer/Abrir


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpaceOrkut
Formato BibTex mendeley Endnote Logotipo do DeGóis Logotipo do Orcid 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.