基于机器学习的语音情感声学特征筛选(Acoustic Feature Selection for Speech Emotion Based on Machine Learning)

Dong Wenqi (董文琪), Wang Han (王涵), Zhang Jingwei (张璟玮)


Abstract
“筛选有效表达情感的声学特征对语音情感研究至关重要。对具有相同或相似声学特征的情感,声学研究中仅使用基频和时长无法有效区分。本研究扩大声学参数的种类和数量,使用三种机器学习方法,筛选出区分情感类型的多组有效声学参数,补充和完善语音情感声学研究的声学特征集。研究发现,区分不同情感所依赖的声学参数、参数数量、参数贡献都不相同,其中频谱和信噪参数发挥重要作用。本研究为语音情感声学分析的参数选择提供参考。”
Anthology ID:
2024.ccl-1.44
Volume:
Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
Month:
July
Year:
2024
Address:
Taiyuan, China
Editors:
Maosong Sun, Jiye Liang, Xianpei Han, Zhiyuan Liu, Yulan He
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
568–576
Language:
Chinese
URL:
https://aclanthology.org/2024.ccl-1.44/
DOI:
Bibkey:
Cite (ACL):
Dong Wenqi, Wang Han, and Zhang Jingwei. 2024. 基于机器学习的语音情感声学特征筛选(Acoustic Feature Selection for Speech Emotion Based on Machine Learning). In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference), pages 568–576, Taiyuan, China. Chinese Information Processing Society of China.
Cite (Informal):
基于机器学习的语音情感声学特征筛选(Acoustic Feature Selection for Speech Emotion Based on Machine Learning) (Wenqi et al., CCL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.ccl-1.44.pdf