The At&t Next-gen Tts System

  title={The At&t Next-gen Tts System},
  author={M. Beutnagel and Alistair Conkie and Juergen Schroeter and Yannis Stylianou and Ann K. Syrdal},
The new AT&T Text-To-Speech (TTS) system for general U.S. English text is based on best-choice components of the AT&T Flextalk TTS, the Festival System from the University of Edinburgh, and ATR’s CHATR system. From Flextalk, it employs text normalization, letter-to-so und, and prosody generation. Festival provides a flexible and modular architecture for easy experimentation and competitive evaluation of different algorithms or modules. In addition, we adopted CHATR’s unit selection algorithms… CONTINUE READING
Highly Cited
This paper has 260 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 164 extracted citations

260 Citations

Citations per Year
Semantic Scholar estimates that this publication has 260 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…