Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Predictive neural networks applied to phoneme recognition

Autor
Freitag, F.; Monte, E.; Salavedra, J.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
5th European Conference on Speech Communication and Technology
Any de l'edició
1997
Data de presentació
1997-09
Llibre d'actes
EUROSPEECH'97: 5th European Conference on Speech Communication and Technology: Rhodes, Greece: 22-25 September 1997
Pàgina inicial
2831
Pàgina final
2834
Repositori
http://hdl.handle.net/2117/88538 Obrir en finestra nova
Resum
In this paper a phoneme recognition system based on predictive neural networks is proposed. Neural networks are used to predict observation vectors of speech frames. The obtained prediction error is used for phoneme recognition as 1) distortion measure on the frame level and 2) as feature, which is statistically modeled by the Rayleigh distribution. Continuous speech phoneme recognition experiments are performed different settings of the system are evaluated.
Citació
Freitag, F., Monte, E., Salavedra, J. Predictive neural networks applied to phoneme recognition. A: European Conference on Speech Communication and Technology. "EUROSPEECH'97: 5th European Conference on Speech Communication and Technology: Rhodes, Greece: 22-25 September 1997". Rhodes: 1997, p. 2831-2834.
Grup de recerca
CNDS - Xarxes de Computadors i Sistemes Distribuïts
IDEAI-UPC Intelligent Data Science and Artificial Intelligence
TALP - Centre de Tecnologies i Aplicacions del Llenguatge i la Parla
VEU - Grup de Tractament de la Parla

Participants