Fourth European Conference on Speech Communication and Technology

Madrid, Spain
September 18-21, 1995

Using Neural Networks to Locate Pitch Accents

Paul Taylor

Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK

This paper describes a technique for producing an auto-segmental representation of an utterances intonation. The technique works in a bottom-up manner by using a recurrent neural network to perform a classification of each framen in the input waveform. The technique correctly identifies 87.5% of pitch accents and boundary tones.

Full Paper

Bibliographic reference.  Taylor, Paul (1995): "Using neural networks to locate pitch accents", In EUROSPEECH-1995, 1345-1348.