WikiSpeech – enabling open source text-to-speech for Wikipedia

John Andersson, Sebastian Berlin, André Costa, Harald Berthelsen, Hanna Lindgren, Nikolaj Lindberg, Jonas Beskow, Jens Edlund, Joakim Gustafson

We present WikiSpeech, an ambitious joint project aiming to (1) make open source text-to-speech available through Wikimedia Foundation’s server architecture; (2) utilize the large and active Wikipedia user base to achieve continuously improving text-to-speech; (3) improve existing and develop new crowdsourcing methods for text-to-speech; and (4) develop new and adapt current evaluation methods so that they are well suited for the particular use case of reading Wikipedia articles out loud while at the same time capable of harnessing the huge user base made available by Wikipedia. At its inauguration, the project is backed by The Swedish Post and Telecom Authority and headed by Wikimedia Sverige, STTS and KTH, but in the long run, the project aims at broad multinational involvement. The vision of the project is freely available text-to-speech for all Wikipedia languages (currently 293). In this paper, we present the project itself and its first steps: requirements, initial architecture, and initial steps to include crowdsourcing and evaluation.

DOI: 10.21437/SSW.2016-16

Cite as

Andersson, J., Berlin, S., Costa, A., Berthelsen, H., Lindgren, H., Lindberg, N., Beskow, J., Edlund, J., Gustafson, J. (2016) WikiSpeech – enabling open source text-to-speech for Wikipedia. Proc. 9th ISCA Speech Synthesis Workshop, 93-99.

author={John Andersson and Sebastian Berlin and André Costa and Harald Berthelsen and Hanna Lindgren and Nikolaj Lindberg and Jonas Beskow and Jens Edlund and Joakim Gustafson},
title={WikiSpeech – enabling open source text-to-speech for Wikipedia},
booktitle={9th ISCA Speech Synthesis Workshop},