Blind Phoneme Segmentation With Temporal Prediction Errors

Roland Thiollière
Roland Thiollière

ACL (Student Research Workshop), pp. 62-68, 2017.

Cited by: 2|Views15
EI

Abstract:

Phonemic segmentation of speech is a critical step of speech recognition systems. We propose a novel unsupervised algorithm based on sequence prediction models such as Markov chains and recurrent neural network. Our approach consists in analyzing the error profile of a model trained to predict speech features frame-by-frame. Specifically,...More

Code:

Data:

Your rating :
0

 

Tags
Comments