论文信息 - Creating a database of speech in noise for unit selection synthesis

Creating a database of speech in noise for unit selection synthesis

This paper describes CMUSIN, 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.

Alan W. Black | Brian Langner

[1] Martine Grice,et al. The SUS test: A method for the assessment of text-to-speech synthesis intelligibility using Semantically Unpredictable Sentences , 1996, Speech Commun..

[2] Maxine Eskénazi,et al. LET's GO: improving spoken dialog systems for the elderly and non-natives , 2003, INTERSPEECH.

[3] Maxine Eskénazi,et al. A study on speech over the telephone and aging , 2001, INTERSPEECH.

[4] Antoine Raux,et al. A unit selection approach to F0 modeling and its application to emphasis , 2003, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721).