Automatic classification of speech and music using neural networks

M. Kashif Saeed Khan; Wasfi G. Al-Khatib; Muhammad Moinuddin

doi:10.1145/1032604.1032620

Automatic classification of speech and music using neural networks

M. Kashif Saeed Khan^*, Wasfi G. Al-Khatib, Muhammad Moinuddin

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

13 Scopus citations

Abstract

The importance of automatic discrimination between speech signals and music signals has evolved as a research topic over recent years. The need to classify audio into categories such as speech or music is an important aspect of many multimedia document retrieval systems. Several approaches have been previously used to discriminate between speech and music data. In this paper, we propose the use of the mean and variance of the discrete wavelet transform in addition to other features that have been used previously for audio classification. We have used Multi-Layer Perceptron (MLP) Neural Networks as a classifier. Our initial tests have shown encouraging results that indicate the viability of our approach.

Original language	English
Title of host publication	MMDB 2004
Subtitle of host publication	Proceedings of the Second ACM International Workshop on Multimedia Databases
Publisher	Association for Computing Machinery (ACM)
Pages	94-99
Number of pages	6
ISBN (Print)	1581139756, 9781581139754
DOIs	https://doi.org/10.1145/1032604.1032620
State	Published - 2004

Publication series

Name	MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases

Keywords

Audio features
Audio signal processing
Content-based indexing
Music speech classification
Neural networks

ASJC Scopus subject areas

General Engineering

Access to Document

10.1145/1032604.1032620

Cite this

Khan, M. K. S., Al-Khatib, W. G., & Moinuddin, M. (2004). Automatic classification of speech and music using neural networks. In MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases (pp. 94-99). (MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases). Association for Computing Machinery (ACM). https://doi.org/10.1145/1032604.1032620

Khan, M. Kashif Saeed ; Al-Khatib, Wasfi G. ; Moinuddin, Muhammad. / Automatic classification of speech and music using neural networks. MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases. Association for Computing Machinery (ACM), 2004. pp. 94-99 (MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases).

@inproceedings{98894791c89a46dbb35bdbec299b20f7,

title = "Automatic classification of speech and music using neural networks",

abstract = "The importance of automatic discrimination between speech signals and music signals has evolved as a research topic over recent years. The need to classify audio into categories such as speech or music is an important aspect of many multimedia document retrieval systems. Several approaches have been previously used to discriminate between speech and music data. In this paper, we propose the use of the mean and variance of the discrete wavelet transform in addition to other features that have been used previously for audio classification. We have used Multi-Layer Perceptron (MLP) Neural Networks as a classifier. Our initial tests have shown encouraging results that indicate the viability of our approach.",

keywords = "Audio features, Audio signal processing, Content-based indexing, Music speech classification, Neural networks",

author = "Khan, {M. Kashif Saeed} and Al-Khatib, {Wasfi G.} and Muhammad Moinuddin",

year = "2004",

doi = "10.1145/1032604.1032620",

language = "English",

isbn = "1581139756",

series = "MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases",

publisher = "Association for Computing Machinery (ACM)",

pages = "94--99",

booktitle = "MMDB 2004",

address = "United States",

}

Khan, MKS, Al-Khatib, WG & Moinuddin, M 2004, Automatic classification of speech and music using neural networks. in MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases. MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases, Association for Computing Machinery (ACM), pp. 94-99. https://doi.org/10.1145/1032604.1032620

Automatic classification of speech and music using neural networks. / Khan, M. Kashif Saeed; Al-Khatib, Wasfi G.; Moinuddin, Muhammad.
MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases. Association for Computing Machinery (ACM), 2004. p. 94-99 (MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automatic classification of speech and music using neural networks

AU - Khan, M. Kashif Saeed

AU - Al-Khatib, Wasfi G.

AU - Moinuddin, Muhammad

PY - 2004

Y1 - 2004

N2 - The importance of automatic discrimination between speech signals and music signals has evolved as a research topic over recent years. The need to classify audio into categories such as speech or music is an important aspect of many multimedia document retrieval systems. Several approaches have been previously used to discriminate between speech and music data. In this paper, we propose the use of the mean and variance of the discrete wavelet transform in addition to other features that have been used previously for audio classification. We have used Multi-Layer Perceptron (MLP) Neural Networks as a classifier. Our initial tests have shown encouraging results that indicate the viability of our approach.

AB - The importance of automatic discrimination between speech signals and music signals has evolved as a research topic over recent years. The need to classify audio into categories such as speech or music is an important aspect of many multimedia document retrieval systems. Several approaches have been previously used to discriminate between speech and music data. In this paper, we propose the use of the mean and variance of the discrete wavelet transform in addition to other features that have been used previously for audio classification. We have used Multi-Layer Perceptron (MLP) Neural Networks as a classifier. Our initial tests have shown encouraging results that indicate the viability of our approach.

KW - Audio features

KW - Audio signal processing

KW - Content-based indexing

KW - Music speech classification

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=20444491279&partnerID=8YFLogxK

U2 - 10.1145/1032604.1032620

DO - 10.1145/1032604.1032620

M3 - Conference contribution

AN - SCOPUS:20444491279

SN - 1581139756

SN - 9781581139754

T3 - MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases

SP - 94

EP - 99

BT - MMDB 2004

PB - Association for Computing Machinery (ACM)

ER -

Khan MKS, Al-Khatib WG, Moinuddin M. Automatic classification of speech and music using neural networks. In MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases. Association for Computing Machinery (ACM). 2004. p. 94-99. (MMDB 2004: Proceedings of the Second ACM International Workshop on Multimedia Databases). doi: 10.1145/1032604.1032620

Automatic classification of speech and music using neural networks

Abstract

Publication series

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this