Issue |
MATEC Web Conf.
Volume 63, 2016
2016 International Conference on Mechatronics, Manufacturing and Materials Engineering (MMME 2016)
|
|
---|---|---|
Article Number | 04047 | |
Number of page(s) | 3 | |
Section | Information Technology, Control and Application | |
DOI | https://doi.org/10.1051/matecconf/20166304047 | |
Published online | 12 July 2016 |
The separability analysis of pitch parameters in speaker recognition
School of Information sci. and Eng., Shandong Univ, Jinan 250100, China
a Corresponding author: herongrong1993@163.com
Aseparability research of prosodic parameters in speaker recognition is studied.The space distribution of the prosodic parameters is drawn using the mean and variance of the speaker pitch parameters,through which the separability of the speaker is obvious.We do a speaker identification experiment with a small corpus,and the experiment results show that speaker identification based on the prosodic parameters is possible. The first-level decision using the prosodic parameters can reduce the candidate corpus effectively,demonstrating the practicability of the pitch parameters.
Key words: speaker recognition / pitch parameters / feature space
© Owned by the authors, published by EDP Sciences, 2016
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.