Title:
声紋モデルを構築する方法、装置、コンピュータデバイス、プログラム及び記憶媒体
Document Type and Number:
Japanese Patent JP6906067
Kind Code:
B2
Abstract:
A method and apparatus for establishing a voiceprint model, a computer device, and a storage medium are described herein. The method includes: collecting speech acoustic features in a speech signal to form a plurality of cluster structures; calculating an average value and a standard deviation of the plurality of cluster structures and then performing coordinate transformation and activation function calculation to obtain a feature vector; and obtaining a voiceprint model based on the feature vector.
Inventors:
Caimoto Satoshi
Ken sect
程 ▲寧▼
Xiao Kyo
Ken sect
程 ▲寧▼
Xiao Kyo
Application Number:
JP2019570559A
Publication Date:
July 21, 2021
Filing Date:
July 06, 2018
Export Citation:
Assignee:
PING AN TECHNOLOGY (SHENZHEN) CO.,LTD.
International Classes:
G10L17/18; G10L17/00
Foreign References:
| US20170160813 | ||||
| US20170358306 |
Other References:
David Snyder et al.,Deep Neural Network Embeddings for Text-Independent Speaker Verification,Interspeech 2017,2017年 8月,p.999-1003
David Snyder et al.,X-Vectors: Robust DNN Embeddings for Speaker Recognition,2018 IEEE International Conference on Acoustics, Speech and Signal Processing,2018年 4月,p.5329-5333
David Snyder et al.,X-Vectors: Robust DNN Embeddings for Speaker Recognition,2018 IEEE International Conference on Acoustics, Speech and Signal Processing,2018年 4月,p.5329-5333
Attorney, Agent or Firm:
Kaji/Suhara Patent Office
Yasuhiko Murayama
Shinya Mitsuhiro
Tatsuhiko Abe
Yasuhiko Murayama
Shinya Mitsuhiro
Tatsuhiko Abe