Robust neural network-based estimation of articulatory features for Czech

Title:

Robust neural network-based estimation of articulatory features for Czech

Creator:

Mizera, Petr and Pollak, Peter

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:8cf61c72-3d3d-431f-94f8-e01a96b8cfd2
uuid:8cf61c72-3d3d-431f-94f8-e01a96b8cfd2
doi:10.14311/NNW.2014.24.027

Subject:

Speech recognition, articulatory features, robust estimation, neural networks, MLP, temporal patterns, and TRAP

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

The article describes a neural network-based articulatory feature (AF) estimation for the Czech speech. First, the relationship between AFs and a Czech phone inventory is defined, and then the estimation based on the MLP neural networks is done. The usage of several speech representations on the input of the MLP classifiers is proposed with the purpose to obtain a robust AF estimation. The realized experiments have proved that an ANN- based AF estimation works very reliably especially in a low noise environment. Moreover, in case the number of neurons in a hidden layer is increased and if the temporal context DCT-TRAP features are used on the input of the MLP network, the AF classification works accurately also for the signals collected in the environments with a high background noise.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2014 Volume:24 | Number:5

Harvested from:

CDK

Metadata only:

false