Reconstructing clean speech from noisy MFCC vectors

Milner, Ben, Darch, Jonathan and Almajai, Ibrahim (2009) Reconstructing clean speech from noisy MFCC vectors. In: 10th Annual Conference of the International Speech Communication Association (INTERSPEECH), 2009-09-06 - 2009-09-10.

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

Abstract

The aim of this work is to reconstruct clean speech solely from a stream of noise-contaminated MFCC vectors, as may be encountered in distributed speech recognition systems. Speech reconstruction is performed using the ETSI Aurora back-end speech reconstruction standard which requires MFCC vectors, fundamental frequency and voicing information. In this work, fundamental frequency and voicing are obtained using maximum a posteriori prediction from input MFCC vectors, thereby allowing speech reconstruction solely from a stream of MFCC vectors. Two different methods to improve prediction accuracy in noisy conditions are then developed. Experimental results first establish that improved fundamental frequency and voicing prediction is obtained when noise compensation is applied. A series of human listening tests are then used to analyse the reconstructed speech quality, which determine the effectiveness of noise compensation in terms of mean opinion scores.

Item Type:	Conference or Workshop Item (Paper)
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Interactive Graphics and Audio Faculty of Science > Research Groups > Smart Emerging Technologies Faculty of Science > Research Groups > Data Science and AI
Depositing User:	Vishal Gautam
Date Deposited:	11 Mar 2011 16:23
Last Modified:	10 Dec 2024 01:14
URI:	https://ueaeprints.uea.ac.uk/id/eprint/23771
DOI:

Actions (login required)

View Item