Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Evaluation of VTLN-Based Voice Conversion for Embedded Speech Synthesis

David Sundermann (1), Guntram Strecha (2), Antonio Bonafonte (1), Harald Höge (3), Hermann Ney (4)

(1) Universitat Politecnica de Catalunya, Spain; (2) Dresden University of Technology, Germany; (3) Siemens AG, Germany; (4) RWTH Aachen University, Germany

Recently, we demonstrated that vocal tract length normalization (VTLN) can be applied to voice conversion tasks. In particular, when the conversion algorithm is performed in time domain, this technique is very resource-efficient and, consequently, suitable for embedded applications. In this paper, we use VTLN-based voice conversion as a novel feature of a small footprint speech synthesizer running on mobile devices. The characteristics of this feature are investigated by means of extensive subjective tests.

Full Paper

Bibliographic reference.  Sundermann, David / Strecha, Guntram / Bonafonte, Antonio / Höge, Harald / Ney, Hermann (2005): "Evaluation of VTLN-based voice conversion for embedded speech synthesis", In INTERSPEECH-2005, 2593-2596.