Fifth International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA 2007)

Florence, Italy
December 13-15, 2007

Methodology of Fundamental Frequency Extraction and Analysis Using Microphone Speech Signal and Vocal Tract Model

Zygmunt Ciota

Department of Microelectronics and Computer Science, Technical University of Lodz, Poland

A model of vocal tract has been presented. According to the dimensions of natural tract, equivalent parameters of the model have been calculated. The proposed model permits to extract important parameters of vocal signal, especially frequency parameters of glottal waves. The proposed system of speech processing permits also for analysis and synthesis of all phonemes. The system is oriented on the verification of speech malfunctions. The improvement of verification process can be improved by using more sophisticated classifiers, like neural networks.
Index Terms. Vocal tract, fundamental frequency, speech verification, neural networks

Full Paper (reprinted with permission from Firenze University Press)

Bibliographic reference.  Ciota, Zygmunt (2007): "Methodology of fundamental frequency extraction and analysis using microphone speech signal and vocal tract model", In MAVEBA-2007, 123-126.