The EASR Corpora of European Portuguese, French, Hungarian and Polish elderly speech

Currently available speech recognisers do not usually work well with elderly speech. This is because several characteristics of speech (e.g. fundamental frequency, jitter, shimmer and harmonic noise ratio) change with age and because the acoustic models used by speech recognisers are typically train...

ver descrição completa

Detalhes bibliográficos
Autor principal: Hämäläinen, A. (author)
Outros Autores: Avelar, J. (author), Rodrigues, S. (author), Dias, J. (author), Kolesinski, A. (author), Fegyó, T. (author), Németh, G. (author), Csobánka, P. (author), Ting, K. (author), Hewson, D. (author)
Formato: conferenceObject
Idioma:eng
Publicado em: 2022
Assuntos:
Automatic speech recognition
Corpus
Elderly speech
Texto completo:http://hdl.handle.net/10071/25545
País:Portugal
Oai:oai:repositorio.iscte-iul.pt:10071/25545

Texto Completo

http://hdl.handle.net/10071/25545

Registos relacionados