| Issue |
SHS Web of Conferences
Volume 25, 2016
ICITCE 2015 – 3rd International Conference on Information Technology and Career Education
|
|
|---|---|---|
| Article Number | 01017 | |
| Number of page(s) | 5 | |
| Section | Education and teaching | |
| DOI | https://doi.org/10.1051/shsconf/20162501017 | |
| Published online | 22 April 2016 | |
Statistical analysis of acoustic characteristics of Tibetan Lhasa dialect speech emotion
Key Lab of China’s National Linguistic Information Technology Northwest University for Nationalities, Lanzhou, Gansu, China
* Corresponding author: 920233231@qq.com
The paper makes a quantitative analysis and comparison on the continuous speech emotion of Lhasa Tibetan in the four basic emotional patterns (happy, surprise, sad, neutral) pitch, energy and time length by experimental phonetics and the linear statistical research methods, found that there is a positive correlation between the Lhasa Tibetan emotional speech and pitch, energy and duration, etc. And the pitch, energy and duration of negative emotion acoustic parameters are bigger than positive emotion, on this basis, drawing the Lhasa Tibetan speech emotion acoustic feature patterns. Compared with the Chinese language and the Tibetan, even though both have the tone prosodic features, they also have significant differences in the acoustic characteristics of the speech emotion.
Key words: Tibetan Lhasa Dialect / Speech Emotion / Acoustic Characteristics
© 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.