Publication: Stereo echo cancellation based on self-organizing maps neural networks
0
0
Issued Date
2019
Resource Type
File Type
application/pdf
Other identifier(s)
2-s2.0-85077962315
Rights Holder(s)
Scopus
Bibliographic Citation
iEECON 2019 - 7th International Electrical Engineering Congress, Proceedings. (2019)
Suggested Citation
Kunarak S. Stereo echo cancellation based on self-organizing maps neural networks. iEECON 2019 - 7th International Electrical Engineering Congress, Proceedings. (2019). doi:10.1109/iEECON45304.2019.8938999 Retrieved from: https://hdl.handle.net/20.500.14740/5416
Author(s)
Abstract
In this paper, the self-organizing maps (SOM) is used to get rid the unwanted sound signal that is also known as the Stereo Echo Cancellation (SEC). SEC is a necessary procedure for reducing undesired noise or echo sound owing that the audiences can get the apparent signal. The echo sounds are sampled as the input and introduce to the SOM neural network process. To guarantee the clarity sound, the Echo Return Loss Enhancement (ERLE) and Mean Square Error (MSE) are shown in the simulation results that the proposed approach is provided outperformance the previous works as Adaptive Filter with Gain and Time-shift, Linear Deep Neural Networks and Feedforward Networks. The proposed method can improve the ERLE around 8 dB and also can reduce the MSE less than 0.0001. © 2019 IEEE.