Georg I. Schlünz

  • Citations Per Year
Learn More
One of the goals of text-to-speech (TTS) systems is to produce natural-sounding synthesised speech. Towards this end various natural language processing (NLP) tasks are performed to model the prosodic aspects of the TTS voice. One of the fundamental NLP tasks being used is the part-of-speech (POS) tagging of the words in the text. This paper investigates(More)
This paper describes the Speect text-to-speech system entry for the Blizzard Challenge 2013. The techniques applied for the tasks of the challenge are described as well as the implementation details for the alignment of the audio books and the text-to-speech system modules. The results of the evaluations are given and discussed.
We introduce a new open source speech synthesis engine and related set of tools: Speect is designed to be a portable and flexible synthesis engine, equally relevant as a research platform and runtime synthesis system in multilingual environments. In this paper we document our approach to the rapid development of British English voices for the 2010 Blizzard(More)
Persons with certain disabilities face barriers to information access and interpersonal communication. Assistive technologies provide workaround solutions to these problems. Augmentative and alternative communication systems aid the person with little or no functional speech to speak out loud. Screen readers and accessible e-books allow a print-disabled(More)
Text-to-speech synthesis can be an empowering communication tool in the hands of the print-disabled or augmentative and alternative communication user. In an effort to improve the naturalness of synthesised speech – and thus enhance the communication experience – we apply the natural language processing tasks of part-of-speech tagging and chunking to the(More)
  • 1