• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

李如玮 (李如玮.) | 潘冬梅 (潘冬梅.) | 李涛 (李涛.) | 刘亚楠 (刘亚楠.) | 张永亚 (张永亚.)

Indexed by:

incoPat zhihuiya

Abstract:

本发明公开一种数字助听器中基于深度学习的双耳声源定位方法,首先将双耳声源信号通过gammatone滤波器分解成若干信道,通过加权系数提取高能量的信道,接着利用头相关函数(head‑related‑transform function, HRTF)提取第一类特征,即耳间时间差(Interaural Time Difference, ITD)和耳间强度差(Interaural Intensity Difference, IID)作为深度学习的输入,将水平面划分为四个象限,缩小定位范围。然后提取头相关传递的第二类特征,即耳间声压差(Interaural Level Difference, ILD)和耳间相位差(Interaural Phase Difference, IPD),最后为了得到更精确的定位,将第一类和第二类的四个特征作为下一个深度学习的输入,从而得到声源定位的方位角。实现在水平面上0度到360度以5度为步长进行72个方位角的精确定位。

Keyword:

Reprint Author's Address:

Email:

Show more details

Related Keywords:

Related Article:

Patent Info :

Type: 发明授权

Patent No.: CN201711397816.2

Filing Date: 2017-12-21

Publication Date: 2021-05-14

Pub. No.: CN108122559B

Applicants: 北京工业大学

Legal Status: 未缴年费

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 17

Affiliated Colleges:

Online/Total:216/10507976
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.