Phoneme Based Text-Prompted Speaker Verification with Multi-Layer Perceptrons
| Tipo de publicação: | Inproceedings |
| Citação: | henn98:rla2c |
| Booktitle: | Speaker Recognition and its Commercial and Forensic Applications (RLA2C), Avignon, France |
| Ano: | 1998 |
| Páginas: | 55-58 |
| URL: | http://diuf.unifr.ch/people/he... |
| Resumo: | Results presented in this paper are obtained in the framework of a text-prompted speaker verification system using Hidden Markov Models (HMMs) and Multi Layer Perceptrons (MLPs). The aims of the study described here are (1) to assess the relative speaker discriminant properties of phonemes with different temporal frame-to-frame context at the input of the MLP's and (2) to study the influence of two sampling techniques of the acoustic vectors while training the MLP's. |
| Palavras-chave: | ANN, Biometrics, MLP, Speaker Verification |
| Autores | |
| Adicionado por: | [] |
| Total mark: | 0 |
|
Anexos
|
|
|
Notas
|
|
|
|
|
|
Tópicos
|
|
|
|
|