3D - Learning Representations From Audio Using Autoencoders

A, Bharathi and J, Prakash (2021) 3D - Learning Representations From Audio Using Autoencoders. In: ICCAP 2021, 7-8 December 2021, Chennai, India.

[thumbnail of PDF]
Text (PDF)
eai.7-12-2021.2314968.pdf - Published Version

Download (2MB) | Preview


Deep learning methods permit us to tackle signal processing challenges from a dissimilar perspective, which is currently overlooked in the composition of music in cinema industry. Audio is inherently added time-sensitive than movie. Audios are encoded using other past methods, resulting in data loss or temporal anomalies. This problem is alleviated by using an auto correlogram with a 3-dimensional view, including time, power, and frequency, to improve accuracy. First, acoustic data should be competently encoded into a compressed format using RNN autoencoder by interrelating with the information. As a result of the compressed format, audio waves should be accurately represented. After that, audio waves are rebuilt into an audio structure with little data loss. The accuracy is improved by 10% by using the RNN encoder and decoder.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: audio signal auto correlogram rnn encoder rnn decoder
Subjects: T Technology > T Technology (General)
Depositing User: EAI Editor IV
Date Deposited: 12 Jan 2022 11:41
Last Modified: 12 Jan 2022 11:41
URI: https://eprints.eudl.eu/id/eprint/9704

Actions (login required)

View Item
View Item