Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Intelligibility of Machine Translation Output in Speech Synthesis

Laura Mayfield Tomokiyo, Kay Peterson, Alan W. Black, Kevin A. Lenzo

Cepstral LLC, USA

One use of text-to-speech synthesis (TTS) is as a component of speechto- speech translation systems. The output of automatic machine translation (MT) can vary widely in quality, however. A synthetic voice that is extremely intelligible on naturally-occurring text may be far less intelligible when asked to render text that is automatically generated. In this paper, we compare the quality of synthesis of naturally-occurring text and its MT counterpart. We find that intelligibility of TTS on MT output is significantly lower than on either naturally-occurring text or semantically unpredictable sentences, and explore the reasons why.

Full Paper

Bibliographic reference.  Tomokiyo, Laura Mayfield / Peterson, Kay / Black, Alan W. / Lenzo, Kevin A. (2006): "Intelligibility of machine translation output in speech synthesis", In INTERSPEECH-2006, paper 1268-Thu2A3O.2.