DeepVoCoder: A CNN Model for Compression and Coding of Narrow Band Speech

DeepVoCoder: A CNN Model for Compression and Coding of Narrow Band Speech

This paper proposes a convolutional neural network (CNN)-based encoder model to compress and code speech signal directly from raw input speech. Although the model can synthesize wideband speech by implicit bandwidth extension, narrowband is preferred for IP telephony and telecommunications purposes....

Full description

Bibliographic Details
Main Authors: Hacer Yalim Keles, Jan Rozhon, H. Gokhan Ilk, Miroslav Voznak
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Convolutional neural network
deep learning
source coding
speech codecs
Online Access:https://ieeexplore.ieee.org/document/8730308/

Internet

https://ieeexplore.ieee.org/document/8730308/

Similar Items