Speech/music discrimination based on wavelets for broadcast programs

Emmanuel Didiot (1) , Irina Illina (1) , Odile Mella (1) , Dominique Fohr (1) , Jean-Paul Haton (1)

1 PAROLE - Analysis, perception and recognition of speech

The problem of speech/music discrimination is a challenging research problem which significantly impacts Automatic Speech Recognition (ASR) performance. This paper proposes new features for the Speech/Music discrimination task. We propose to use a decomposition of the audio signal based on wavelets, which allows a good analysis of non stationary signal like speech or music. We compute different energy types in each frequency band obtained from wavelet decomposition. Two class/non-class classifiers are used : one for speech/non-speech, one for music/non-music. On the broadcast test corpus, the proposed wavelet approach gives better results than the MFCC one. For instance, we have a significant relative improvements of the error rate of 39% for the speech/music discrimination task.

Mots clés: Speech/music discrimination; wavelets; static and dynamic parameters; long-term parameters; classifiers fusion

Domaines: Informatique et langage [cs.CL]

Emmanuel Didiot, Irina Illina, Odile Mella, Dominique Fohr, Jean-Paul Haton. Speech/music discrimination based on wavelets for broadcast programs. 2006, pp.151. ⟨hal-00103554⟩