An investigation into the correlation and prediction of acoustic speech features from MFCC vectors

Darch, J., Milner, B. P., Almajai, I. and Vaseghi, S. V. (2007) An investigation into the correlation and prediction of acoustic speech features from MFCC vectors. In: IEEE International Conference on Acoustics, Speech and Signal Processing, 2007-04-15 - 2007-04-20.

Full text not available from this repository. (Request a copy)

Abstract

This work develops a statistical framework to predict acoustic features (fundamental frequency, formant frequencies and voicing) from MFCC vectors. An analysis of correlation between acoustic features and MFCCs is made both globally across all speech and within phoneme classes, and also from speaker-independent and speaker-dependent speech. This leads to the development of both a global prediction method, using a Gaussian mixture model (GMM) to model the joint density of acoustic features and MFCCs, and a phoneme-specific prediction method using a combined hidden Markov model (HMM)-GMM. Prediction accuracy measurements show the phoneme-dependent HMM-GMM system to be more accurate which agrees with the correlation analysis. Results also show prediction to be more accurate from speaker-dependent speech which also agrees with the correlation analysis

Item Type: Conference or Workshop Item (Paper)
Faculty \ School: Faculty of Science > School of Computing Sciences
Related URLs:
Depositing User: Vishal Gautam
Date Deposited: 05 Apr 2011 07:32
Last Modified: 22 Apr 2020 09:05
URI: https://ueaeprints.uea.ac.uk/id/eprint/22298
DOI: 10.1109/ICASSP.2007.366950

Actions (login required)

View Item View Item