Adaptive Noise Cancellation Using a Fully Connected Network: A Lesson Learned
6th International Conference on Information Technology, InCIT 2022
; : 111-114, 2022.
Article
in English
| Scopus | ID: covidwho-2304596
ABSTRACT
Ambient noise causes annoying difficulty for listeners, especially in online learning and work-from-home environments such as during the COVID-19 pandemic. The aim of this work was to employ the neural network to mitigate such ambient noise in the online environment. The software was designed, implemented, and tested on 4 types of noise. The algorithm used was a fully connected network. The results indicated that the standard fully connected network might not be an effective solution for a specific situation. Nonetheless, the processing time was very low, making it possible for real-time application on standalone devices. The implementation using leaky ReLu, creating leaky networks, offered slightly better results in English speeches, i.e. an average of 1.382 and 0.4389 in the PESQ and STOI, respectively. The Thai leaky networks, on another hand, exhibited an average of 3.111 and 0.7096 in PESQ and STOI, respectively. © 2022 IEEE.
artificial intelligence; fully connected network; leaky ReLu; noise cancellation; speech enhancement; Acoustic noise; Noise abatement; Spurious signal noise; Adaptive noise cancellations; Ambient noise; Fully connected networks; Home environment; Neural-networks; Online environments; Online learning; Online work; Software testing
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
6th International Conference on Information Technology, InCIT 2022
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS