---
title: "On the Generalization Capability of Multi-Layered Networks in the Extraction of Speech Properties"
authors:
  - "Renato de Mori"
  - "Yoshua Bengio"
  - "Piero Cosi"
doi: ""
url: "https://ijcai.org/proceedings/1989/244"
pdf: "https://ijcai.org/proceedings/1989/0244.pdf"
venue: "Proceedings of the Eleventh International Joint Conference on Artificial Intelligence"
year: 1989
pages: "1531-1535"
track: "Speech and Natural Language"
keywords:
---

# On the Generalization Capability of Multi-Layered Networks in the Extraction of Speech Properties

Renato de Mori, Yoshua Bengio, Piero Cosi

*Proceedings of the Eleventh International Joint Conference on Artificial Intelligence*, 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.