Fifth ISCA ITRW on Speech Synthesis

June 14-16, 2004
Pittsburgh, PA, USA

Creating a Database of Speech in Noise for Unit Selection Synthesis

Brian Langner, Alan W. Black

Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA

This paper describes CMU SIN, a new database of speech in noise that can be used for unit selection speech synthesis. We describe a process that can be used to elicit speech in noise and how to use that as part of building a synthetic voice that speaks in noise. Details of the database we constructed, as well as some preliminary analysis and future goals of this work, are also included.

Full Paper

Bibliographic reference.  Langner, Brian / Black, Alan W. (2004): "Creating a database of speech in noise for unit selection synthesis", In SSW5-2004, 229-230.