The application research of speech feature extraction based on the manifold learning

DOI

10.2991/iccsee.2013.201How to use a DOI?

Keywords

manifold learning, MFCC-Manifold, geodesic distance, feature extraction

Abstract

Traditional MFCC phonetic feature will lead a slower learning speed on account of it has high dimension and is large in data quantities. In order to solve this problem, we introduce a manifold learning, putting forward a new extraction method of MFCC-Manifold phonetic feature. We can reduce dimensions by making use of ISOMAP algorithm which bases on the classical MDS (Multidimensional scaling). Introducing geodesic distance to replace the original European distance data will make twenty-four dimensional data, which using the traditional MFCC feature extraction down to two dimensional data. Experiments prove that MFCC - Manifold feature extraction methods has achieved a satisfactory effect in data volume reduction

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Penghao Zhang
AU  - Li Wang
PY  - 2013/03
DA  - 2013/03
TI  - The application research of speech feature extraction based on the manifold learning
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 796
EP  - 799
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.201
DO  - 10.2991/iccsee.2013.201
ID  - Zhang2013/03
ER  -