Frame-Level Audio Feature Extraction Using AdaBoost

@inproceedings{Casagrande2005FrameLevelAF,
  title={Frame-Level Audio Feature Extraction Using AdaBoost},
  author={Norman Casagrande and Douglas Eck and Bal{\'a}zs K{\'e}gl},
  booktitle={ISMIR},
  year={2005}
}
In this paper we adapt an AdaBoost-based image processing algorithm to the task of predicting whether an audio signal contains speech or music. We derive a frame-level discriminator that is both fast and accurate. Using a simple FFT and no built-in prior knowledge of signal structure we obtain an accuracy of 88% on frames sampled at 20ms intervals. When we smooth the output of the classifier with the output of the previous 40 frames our forecast rate rises to 93% on the Scheirer-Slaney… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-10 of 10 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 11 references

Schapire . A Brief Introduction to Boosting

  • E. Robert
  • 1999

Sinewave speech/nonspeech perception: An fMRI study

  • Einat Liebenthal, Jeffrey R. Binder, Rebecca L. Piorkowski, Robert E. Remez
  • The Journal of the Acoustical Society of America…
  • 1992

Similar Papers

Loading similar papers…