On the Generalization Capability of Multi-Layered Networks in the Extraction of Speech Properties
Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Speech and Natural Language. Pages 1531-1535.
Abstract
The paper describes a speech coding system based on an ear model followed by a set of MultiLayer Networks (MLN). MLNs are trained to learn how to recognize articulatory features like the place and manner of articulation. Experiments are performed on 10 English vowels showing a recognition rate higher than 95% for new speakers. When features are used for recognition, comparable results are obtained for vowels and diphthongs not used for training and pronounced by new speakers. This suggests that MLNs suitably fed by the data computed by an ear model have good generalization capabilities over new speakers and new sounds.
@inproceedings{ijcai1989p244,
title = {On the Generalization Capability of Multi-Layered Networks in the Extraction of Speech Properties},
author = {de Mori, Renato and Bengio, Yoshua and Cosi, Piero},
booktitle = {Proceedings of the Eleventh International Joint Conference on
Artificial Intelligence, {IJCAI-89}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {N. S. Sridharan},
pages = {1531--1535},
year = {1989},
month = {8},
note = {Speech and Natural Language},
url = {https://ijcai.org/proceedings/1989/244},
}
TY - CPAPER TI - On the Generalization Capability of Multi-Layered Networks in the Extraction of Speech Properties AU - de Mori, Renato AU - Bengio, Yoshua AU - Cosi, Piero T2 - Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, IJCAI-89 PB - International Joint Conferences on Artificial Intelligence PY - 1989 SP - 1531 EP - 1535 UR - https://ijcai.org/proceedings/1989/244 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
