A Combination of Data Mining Method with Context-Based State Transfer for Speech/Music Discrimination

Author

Yan, Qin ; Wu, Qiong ; Deng, Haojiang ; Wang, JinLin

Author_Institution

Sch. of Inf. & Eng., Hohai Univ., Nanjing, China

fYear

2009

fDate

24-26 Sept. 2009

Firstpage

1

Lastpage

4

Abstract

In our previous work, a speech/music classifier is proposed on the basis of the feature subset selection (FSS) tool and oblique decision tree induced by the algorithm OC1. In this paper, we endeavor to improve it by state transfer (ST) strategy whose aim is to refine the classification results, according to the fact that adjacent segments in one audio file have strong relevance to each other. The proposed algorithm is evaluated by a set of 5-to-11-minute 504 audio files of different types of speech and music in three signal-to-noise ratio (SNR) levels: 30 dB, 20 dB and 10 dB. The results show that ST strategy averagely improves the accuracy for music by 3.3% at 10 dB and 2.3% at 20 dB while keeping accuracy rate of speech almost unchanged. The speech classification rate is also lifted by 5.7% at 10 dB on average.

Keywords

data mining; decision trees; feature extraction; music; signal classification; speech processing; FSS tool; audio files; context-based state transfer strategy; data mining method; decision tree; feature subset selection; music discrimination; speech classification; Classification tree analysis; Data engineering; Data mining; Decision trees; Frequency selective surfaces; Hidden Markov models; Multiple signal classification; Real time systems; Signal to noise ratio; Speech analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Wireless Communications, Networking and Mobile Computing, 2009. WiCom '09. 5th International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-3692-7

Electronic_ISBN

978-1-4244-3693-4

Type

conf

DOI

10.1109/WICOM.2009.5303331

Filename

5303331