- Authors:
-
Hoelper,
C.
,
Frankort,
A.
,
Erdmann,
C.
- Book Title:
- Proceedings of International Student Conference on Electrical Engineering (POSTER)
- Address:
- Prague
- Date:
-
May. 2003
- Language:
- English
Abstract
For use in offline speech processing systems a novel algorithm has been developed, that classifies clean speech segments as voiced, unvoiced, or silence respectively. This decision is needed, e.g., in source controlled speech coders which treat voiced, unvoiced, and silent segments differently, always yielding best speech quality at minimum bit rate. The classifier is based on a combination of features, extracted from the signal in the time domain. Besides the energy, a novel measure, repre-senting the unsteadiness of the speech, is proposed. Non-realtime coding allows iterative refinement of the classification using the cepstral distance. Another advantage is the adjustment of the decision thresholds to the properties of the individual speech file. The new classification scheme was tested in speech storage systems with the AMR codec.
Download
BibTeX
- Copyright © by IKS
hoelper03.pdf -
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
