Generating intelligible audio speech from visual speech

Le Cornu, Thomas and Milner, Ben P. (2017) Generating intelligible audio speech from visual speech. IEEE Transactions on Audio, Speech, and Language Processing, 25 (9). pp. 1447-1457. ISSN 1558-7916

[img]
Preview
PDF (Accepted manuscript) - Submitted Version
Download (989kB) | Preview

Abstract

This work is concerned with generating intelligible audio speech from a video of a person talking. Regression and classification methods are proposed first to estimate static spectral envelope features from active appearance model (AAM) visual features. Two further methods are then developed to incorporate temporal information into the prediction - a feature-level method using multiple frames and a model-level method based on recurrent neural networks. Speech excitation information is not available from the visual signal, so methods to artificially generate aperiodicity and fundamental frequency are developed. These are combined within the STRAIGHT vocoder to produce a speech signal. The various systems are optimised through objective tests before applying subjective intelligibility tests that determine a word accuracy of 85% from a set of human listeners on the GRID audio-visual speech database. This compares favourably with a previous regression-based system that serves as a baseline which achieved a word accuracy of 33%.

Item Type: Article
Faculty \ School: Faculty of Science > School of Computing Sciences
Depositing User: Pure Connector
Date Deposited: 07 Jul 2017 05:05
Last Modified: 22 Apr 2020 14:31
URI: https://ueaeprints.uea.ac.uk/id/eprint/64052
DOI: 10.1109/TASLP.2017.2716178

Actions (login required)

View Item View Item