Sistemas de adaptação ao locutor utilizando autovozes. / Speaker adaptation system using eigenvoices.
AUTOR(ES)
Liselene de Abreu Borges
DATA DE PUBLICAÇÃO
2001
RESUMO
This present work describe two speaker adaptation technique, using a small amount of adaptation data, for a speech recognition system. These techniques are Maximum Likelihood Linear Regression (MLLR) and Eigenvoices. Both re-estimates the mean of a continuous density Hidden Markov Model system. MLLR technique estimates a set of linear transformations for mean parameters of a Gaussian system. The eigenvoice technique is based on a previous knowledge about speaker variation. For obtaining this previous knowledge, that are retained in eigenvoices, it necessary to apply principal component analysis (PCA). We make adaptation tests over an isolated word recognition system, restrict vocabulary. If a large amount of adaptation data is available (up to 70% of all vocabulary) Eigenvoices technique does not appear to be a good implementation if compared with the MLLR technique. Now, when just a small amount of adaptation data is available (less than 15 % of all vocabulary), Eigenvoices technique get better results than MLLR technique.
ASSUNTO(S)
autovozes reconhecimento de voz adaptação ao locutor eigenvoices speaker adaptation speech recognition
Documentos Relacionados
- Sistema de reconhecimento de locutor utilizando redes neurais artificiais
- Adaptação de locutor em sistema de reconhecimento de fala contínua empregando "Eigenvoices"
- Identificação de locutor usando modelos de misturas de gaussianas.
- Reconhecimento automático do locutor com redes neurais pulsadas.
- Gait-pattern adaptation algorithms using neural network