Representing nonspeech audio signals through speech classification models

  title={Representing nonspeech audio signals through speech classification models},
  author={Huy Phan and Lars Hertel and Marco Maa\ss and Radoslaw Mazur and Alfred Mertins},
The human auditory system is very well matched to both human speech and environmental sounds. Therefore, the question arises whether human speech material may provide useful information for training systems for analyzing nonspeech audio signals, such as in a recognition task. To find out how similar nonspeech signals are to speech, we measure the closeness between target nonspeech signals and different basis speech categories via a speech classification model. The speech similarities are… CONTINUE READING
10 Citations
28 References
Similar Papers


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


Publications referenced by this paper.
Showing 1-10 of 28 references

The DARPA speech recognition research database: Specifications and status

  • W. Fisher, G. Doddington, K. Goudie-Marshall
  • Proc. DARPA Workshop on Speech Recognition, 1986…
  • 1986
Highly Influential
7 Excerpts

Similar Papers

Loading similar papers…