Robust Voicing Detection Using a Multi-Layer Perceptrons Neural Network

Robust Voicing Detection Using a Multi-Layer Perceptrons Neural Network

In the next generation of mobile systems more efficient speech classification algorithms are required, above all in the presence of background noise. In this context, voicing detection is a crucial point in the perceived quality and naturalness of a very low bit-rate speech coder. The paper presents a neural based approach to robust voiced/unvoiced speech classification in mobile environments. The results show that the performance of the neural classifier proposed in the presence of various types of background noise is better than that of traditional methods.

F. Beritelli – C. Randieri

The 6th IEEE International Workshop on intelligent Signal Processing and Communication Systems, Vol. I
5-6 November 1998, Melbourne Australia, pp. 123-127.

The IEEE is the world’s largest professional association advancing innovation and technological excellence for the benefit of humanity. IEEE and its members inspire a global community to innovate for a better tomorrow through its highly-cited publications, conferences, technology standards, and professional and educational activities. IEEE is the trusted “voice” for engineering, computing and technology information around the globe.

You must belogged in to post a comment.

Intellisystem Technologies