IEICE TRANSACTIONS on Information
Encoding Detection and Bit Rate Classification of AMR-Coded Speech Based on Deep Neural Network
Summary :
A method for encoding detection and bit rate classification of AMR-coded speech is proposed. For each texture frame, 184 features consisting of the short-term and long-term temporal statistics of speech parameters are extracted, which can effectively measure the amount of distortion due to AMR. The deep neural network then classifies the bit rate of speech after analyzing the extracted features. It is confirmed that the proposed features provide better performance than the conventional spectral features designed for bit rate classification of coded audio.
- Publication
- IEICE TRANSACTIONS on Information Vol.E101-D No.1 pp.269-272
- Publication Date
- 2018/01/01
- Publicized
- 2017/10/20
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2017EDL8155
- Type of Manuscript
- LETTER
- Category
- Speech and Hearing
Authors
Seong-Hyeon SHIN
Kwangwoon University
Woo-Jin JANG
Kwangwoon University
Ho-Won YUN
Kwangwoon University
Hochong PARK
Kwangwoon University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Seong-Hyeon SHIN, Woo-Jin JANG, Ho-Won YUN, Hochong PARK, "Encoding Detection and Bit Rate Classification of AMR-Coded Speech Based on Deep Neural Network" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 1, pp. 269-272, January 2018, doi: 10.1587/transinf.2017EDL8155.
Abstract: A method for encoding detection and bit rate classification of AMR-coded speech is proposed. For each texture frame, 184 features consisting of the short-term and long-term temporal statistics of speech parameters are extracted, which can effectively measure the amount of distortion due to AMR. The deep neural network then classifies the bit rate of speech after analyzing the extracted features. It is confirmed that the proposed features provide better performance than the conventional spectral features designed for bit rate classification of coded audio.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDL8155/_p
Copy
@ARTICLE{e101-d_1_269,
author={Seong-Hyeon SHIN, Woo-Jin JANG, Ho-Won YUN, Hochong PARK, },
journal={IEICE TRANSACTIONS on Information},
title={Encoding Detection and Bit Rate Classification of AMR-Coded Speech Based on Deep Neural Network},
year={2018},
volume={E101-D},
number={1},
pages={269-272},
abstract={A method for encoding detection and bit rate classification of AMR-coded speech is proposed. For each texture frame, 184 features consisting of the short-term and long-term temporal statistics of speech parameters are extracted, which can effectively measure the amount of distortion due to AMR. The deep neural network then classifies the bit rate of speech after analyzing the extracted features. It is confirmed that the proposed features provide better performance than the conventional spectral features designed for bit rate classification of coded audio.},
keywords={},
doi={10.1587/transinf.2017EDL8155},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Encoding Detection and Bit Rate Classification of AMR-Coded Speech Based on Deep Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 269
EP - 272
AU - Seong-Hyeon SHIN
AU - Woo-Jin JANG
AU - Ho-Won YUN
AU - Hochong PARK
PY - 2018
DO - 10.1587/transinf.2017EDL8155
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2018
AB - A method for encoding detection and bit rate classification of AMR-coded speech is proposed. For each texture frame, 184 features consisting of the short-term and long-term temporal statistics of speech parameters are extracted, which can effectively measure the amount of distortion due to AMR. The deep neural network then classifies the bit rate of speech after analyzing the extracted features. It is confirmed that the proposed features provide better performance than the conventional spectral features designed for bit rate classification of coded audio.
ER -
English
