Speech Synthesizers have traditionally been built on carefully read speech that is recorded in studio environment. Such voices are suboptimal for use in noisy conditions, which is inevitable in a majority of deployed speech systems. In this work, we attempt to modify the output of the speech synthesizers to make it more appropriate for noisy environments. Comparison of spectral and prosodic features of speech in noise and results of some conversion techniques are presented.
Index Terms: speech synthesis, speech in noise, companding
Cite as: Anumanchipalli, G.K., Muthukumar, P.K., Nallasamy, U., Parlikar, A., Black, A.W., Langner, B. (2010) Improving speech synthesis for noisy environments. Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7), 154-159
@inproceedings{anumanchipalli10_ssw,
author={Gopala Krishna Anumanchipalli and Prasanna Kumar Muthukumar and Udhyakumar Nallasamy and Alok Parlikar and Alan W. Black and Brian Langner},
title={{Improving speech synthesis for noisy environments}},
year=2010,
booktitle={Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7)},
pages={154--159}
}