Speech/music discrimination by detection: Assessment of time series events using ROC graphs

Author

Alnadabi, Muhammad ; Johnstone, Sherri

Author_Institution

Sultan Qaboos Univ.

fYear

2009

fDate

23-26 March 2009

Firstpage

1

Lastpage

5

Abstract

This paper suggests the application of the Receiver Operating Characteristics (ROC) graph to assess the performance of any speech/music discrimination method. ROC graphs are applied in the field of speech/music discrimination to assess the Time Series Events (TSE) method. The discrimination problem is viewed as two detection problems: detection of speech and detection of music. It was found that the optimal feature for detecting speech was silence with a true positive rate of 0.9 and false positive rate of 0.14, whilst the optimal feature for music was non-zero crossing rate NZCR with a true positive rate of 0.71 and false positive rate of 0.08.

Keywords

graph theory; music; probability; signal classification; speech recognition; time series; ROC graph; audio classification; music detection; music discrimination method; optimal feature; probability; receiver operating characteristic; speech detection; speech discrimination method; time series event; Computer vision; Counting circuits; Equations; Event detection; Frequency; Multiple signal classification; Sampling methods; Speech recognition; Speech recognition; audio classification; audio discrimination; music detection; roc;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Signals and Devices, 2009. SSD '09. 6th International Multi-Conference on

Conference_Location

Djerba

Print_ISBN

978-1-4244-4345-1

Electronic_ISBN

978-1-4244-4346-8

Type

conf

DOI

10.1109/SSD.2009.4956746

Filename

4956746