Least relative entropy for voiced/unvoiced speech classification

Darren K. Emge, Tulay Adali, M. Kemal Sonmez

Research output: Contribution to conferencePaperpeer-review

1 Scopus citations


The aim of this work is to develop a flexible and efficient approach to the classification of the ratio of voiced to unvoiced excitation sources in continuous speech. To achieve this aim we adopt a probabilistic neural network approach. This is accomplished by designing a multi layer perceptron classifier trained by steepest descent minimization of the Least Relative Entropy (LRE) cost function. By using the LRE cost function we can directly output the ratio, as a probability, of excitation source, voiced to unvoiced, for a given speech segment. These output probabilities can then be used directly in other applications, such as low bit rate coders.

Original languageEnglish (US)
Number of pages5
StatePublished - 1999
Externally publishedYes
EventInternational Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA
Duration: Jul 10 1999Jul 16 1999


OtherInternational Joint Conference on Neural Networks (IJCNN'99)
CityWashington, DC, USA

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence


Dive into the research topics of 'Least relative entropy for voiced/unvoiced speech classification'. Together they form a unique fingerprint.

Cite this