Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Building an English Speech Synthesis System from a Japanese ALS Patientís Voice

Akemi Iida (1), Jun Ito (1), Shimpei Kajima (2), Tsutomu Sugawara (2)

(1) Tokyo University of Technology, Japan; (2) Sophia University, Japan

This paper reports on the development of an English speech synthesis system for a Japanese amyotropic lateral sclerosis patient as part of the project of developing a bilingual communication aid for this patient. The patient had a tracheotomy three years ago and anticipates the possibility of losing his phonatory function. His English speech database for Festival, a free speech synthesis system, was generated from his reading of a US diphone list. There were two problems with the recording. The first was the noise that the artificial ventilator made and the second was his difficulty in pronouncing English. Although the speakerís English database was successfully built by Festvox and the voice was recognized as his voice, the utterance was unintelligible. We therefore proposed reconstructing the patientís database by partially combining it with an English native speakerís database. Results showed that the proposed approach can be promising for those facing this problem.

Full Paper

Bibliographic reference.  Iida, Akemi / Ito, Jun / Kajima, Shimpei / Sugawara, Tsutomu (2006): "Building an English speech synthesis system from a Japanese ALS patient≤s voice", In INTERSPEECH-2006, paper 1948-Wed3A3O.5.