Application of symbolic machine learning to audio signal segmentation

Authors:
Arimantas Raškinis;Gailius Raškinis
Affiliations:
Center of Computational Linguistics, Vytautas Magnus University, Kaunas, Lithuania;Center of Computational Linguistics, Vytautas Magnus University, Kaunas, Lithuania
Venue:
Nonlinear Speech Modeling and Applications
Year:
2005

Citing 3
Cited 0

Inferring decision trees using the minimum description length principle

Information and Computation
Automatic segmentation and labelling of multi-lingual speech data

Speech Communication
CHARADE: a rule system learning system

IJCAI'87 Proceedings of the 10th international joint conference on Artificial intelligence - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we address a data-driven approach to the problem of automatic segmentation of speech and music into phones and notes respectively that makes use of symbolic machine learning techniques. The whole segmentation process is subdivided into four steps: series of non-linear transformations are used for building first-order features that allow easy detection of segmentation candidates, second-order features that describe sound properties in the neighborhood of a segmentation candidate are developed, the set of segmentation candidates is transformed into machine learning data set by labeling candidates in accordance to the annotated speech corpus, and supervised symbolic machine learning methods are applied resulting in segmentation rules.