Publication result detail

Classification of Transmission Channels by Speech Signal Processing

KOPŘIVA, T.; ATASSI, H.; HUSSAIN, A.

Original Title

Classification of Transmission Channels by Speech Signal Processing

English Title

Classification of Transmission Channels by Speech Signal Processing

Type

Paper in proceedings (conference paper)

Original Abstract

The paper deals with the classification of five different transmission channels by applying speech signal processing techniques. The channels considered are: GSM, two PSTN channels and two VoIP channels. For training and testing purpose, a speech database called SPLAB TranCh was constructed. The speech signals of this corpus originally come from well-known TIMIT database, where each utterance passed through each mentioned transmission channel. The main objective of this work is to find optimal features and classification technique that yield best classification accuracy. Several types of features, including MFCC, LPCC and spectral characteristics were put under examination. The best features were identified by using the mRMR algorithm. Various classifiers were tested as well. The results suggested that the classification of transmission channels can be performed with high accuracy (around 92%).

English abstract

The paper deals with the classification of five different transmission channels by applying speech signal processing techniques. The channels considered are: GSM, two PSTN channels and two VoIP channels. For training and testing purpose, a speech database called SPLAB TranCh was constructed. The speech signals of this corpus originally come from well-known TIMIT database, where each utterance passed through each mentioned transmission channel. The main objective of this work is to find optimal features and classification technique that yield best classification accuracy. Several types of features, including MFCC, LPCC and spectral characteristics were put under examination. The best features were identified by using the mRMR algorithm. Various classifiers were tested as well. The results suggested that the classification of transmission channels can be performed with high accuracy (around 92%).

Keywords

Transmission channel, recognition, SVM, Feature, Classifier.

Key words in English

Transmission channel, recognition, SVM, Feature, Classifier.

Authors

KOPŘIVA, T.; ATASSI, H.; HUSSAIN, A.

RIV year

2014

Released

02.07.2013

ISBN

978-1-4799-0402-0

Book

36th International Conference on Telecommunications and Signal processing

Pages from

100

Pages to

103

Pages count

4

BibTex

@inproceedings{BUT103102,
  author="Tomáš {Kopřiva} and Hicham {Atassi} and Amir {Hussain}",
  title="Classification of Transmission Channels by Speech Signal Processing",
  booktitle="36th International Conference on Telecommunications and Signal processing",
  year="2013",
  pages="100--103",
  isbn="978-1-4799-0402-0"
}