Title:
METHOD AND APPARATUS FOR DETECTING PLURALITY OF TYPES OF SOUND EVENTS
Document Type and Number:
WIPO Patent Application WO/2022/001245
Kind Code:
A1
Abstract:
A method of detecting a plurality of types of sound events, comprising: extracting a sound source matrix from sound source data (S100); inputting the sound source matrix into a trained feature extraction network to extract a feature matrix of a sound event (S200); inputting the feature matrix into a trained weight gating loop layer, and on the basis of weights of preceding vectors in a feature matrix and a weight matrix of the weight gating loop layer, weighting corresponding subsequent vectors in the feature matrix to obtain a weighted feature matrix (S300); inputting the weighted feature matrix into a fully connected layer, and by means of the full connection, acquiring a probability matrix, the number of dimensions of the probability matrix corresponding to the number of classifications of sound events (S400); on the basis of the probability matrix, and determining a target sound event that has occurred (S600). The sound source matrix can be stored in a blockchain.
Inventors:
LIU BOQING (CN)
WANG JIANZONG (CN)
ZHANG ZHIYONG (CN)
CHENG NING (CN)
WANG JIANZONG (CN)
ZHANG ZHIYONG (CN)
CHENG NING (CN)
Application Number:
PCT/CN2021/083752
Publication Date:
January 06, 2022
Filing Date:
March 30, 2021
Export Citation:
Assignee:
PING AN TECH SHENZHEN CO LTD (CN)
International Classes:
G10L17/02; G10L17/04; G10L17/18; G10L17/22
Foreign References:
| CN112309405A | 2021-02-02 | |||
| CN106248801A | 2016-12-21 | |||
| CN108648748A | 2018-10-12 | |||
| CN111723874A | 2020-09-29 | |||
| CN110751955A | 2020-02-04 | |||
| CN106356052A | 2017-01-25 | |||
| US20200105293A1 | 2020-04-02 |
Other References:
WANG JINJIA;CUI LIN;YANG QIAN;JI SHAONAN: "General Audio Tagging Based on Attention-Gated Convolutional Recurrent Neural Network", JOURNAL OF FUDAN UNIVERSITY(NATURAL SCIENCE), vol. 59, no. 3, 15 June 2020 (2020-06-15), pages 360 - 367, XP055884007, ISSN: 0427-7104, DOI: 10.15943/j.cnki.fdxb-jns.2020.03.016
YANG DE-JU;MA LIANG-LI;TAN LIN-SHAN;PEI JING-JING: "End-to-end Speech Recognition based on Gated Convolutional Neural Network and CTC", COMPUTER ENGINEERING AND DESIGN, vol. 41, no. 9, 16 September 2020 (2020-09-16), pages 2650 - 2654, XP055884012, ISSN: 1000-7024, DOI: 10.16208/j.issn1000-7024.2020.09.037
YANG DE-JU;MA LIANG-LI;TAN LIN-SHAN;PEI JING-JING: "End-to-end Speech Recognition based on Gated Convolutional Neural Network and CTC", COMPUTER ENGINEERING AND DESIGN, vol. 41, no. 9, 16 September 2020 (2020-09-16), pages 2650 - 2654, XP055884012, ISSN: 1000-7024, DOI: 10.16208/j.issn1000-7024.2020.09.037
Attorney, Agent or Firm:
SL INTELLECTUAL PROPERTY CO., LTD. (CN)
Download PDF: