Using multi-stream hierarchical deep neural network to extract deep audio feature for acoustic event detection

2017 ◽  
Vol 77 (1) ◽  
pp. 897-916 ◽  
Author(s):  
Yanxiong Li ◽  
Xue Zhang ◽  
Hai Jin ◽  
Xianku Li ◽  
Qin Wang ◽  
...  
2020 ◽  
Vol 9 (4) ◽  
pp. 1387-1393
Author(s):  
Suk-Hwan Jung ◽  
Yong-Joo Chung

In this study, we attempted to find the optimal hyper-parameters of the convolutional recurrent neural network (CRNN) by investigating its performance on acoustic event detection. Important hyper-parameters such as the input segment length, learning rate, and criterion for the convergence test, were determined experimentally. Additionally, the effects of batch normalization and dropout on the performance were measured experimentally to obtain their optimal combination. Further, we studied the effects of varying the batch data on every iteration during the training. From the experimental results using the TUT sound events synthetic 2016 database, we obtained optimal performance with a learning rate of 1/10000.  We found that a longer input segment length aided performance improvement, and batch normalization was far more effective than dropout. Finally, performance improvement was clearly observed by varying the starting points of the batch data for each iteration during the training.


2019 ◽  
Vol 38 (8) ◽  
pp. 3433-3453 ◽  
Author(s):  
Xianjun Xia ◽  
Roberto Togneri ◽  
Ferdous Sohel ◽  
Yuanjun Zhao ◽  
Defeng Huang

Sign in / Sign up

Export Citation Format

Share Document