A Sound Masking Signal Generation Method Based on Chinese Pronunciation Characteristics
Authors
Xiaofeng Ma, Peng Zhang, Qiuyun Hao, Xiaoxia Chen, Yanhong Fan, Jingsai Jiang, Ye Li
Corresponding Author
Xiaofeng Ma
Available Online April 2015.
- DOI
- 10.2991/ameii-15.2015.186How to use a DOI?
- Keywords
- Sound masking; Speech privacy; Chinese pronunciation characteristics
- Abstract
Sound masking is a technique to protect the speech privacy of confidential talks in a room. Most of the existing masking signals sometimes become noise sources, and result in a negative impact on the people in the room. This paper proposes a new method for generating masking signals. The synthesis of the new masking signal is based on Chinese pronunciation characteristics and the statistical properties. Since its statistical properties are similar to those of human’s voice, the proposed method is more difficult to be deciphered, and can improve the masking effect and reduce the impact on people's psychology and physiology.
- Copyright
- © 2015, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Xiaofeng Ma AU - Peng Zhang AU - Qiuyun Hao AU - Xiaoxia Chen AU - Yanhong Fan AU - Jingsai Jiang AU - Ye Li PY - 2015/04 DA - 2015/04 TI - A Sound Masking Signal Generation Method Based on Chinese Pronunciation Characteristics BT - Proceedings of the International Conference on Advances in Mechanical Engineering and Industrial Informatics PB - Atlantis Press SP - 1008 EP - 1012 SN - 2352-5401 UR - https://doi.org/10.2991/ameii-15.2015.186 DO - 10.2991/ameii-15.2015.186 ID - Ma2015/04 ER -