5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Methods for Optimal Text Selection

Jan P. H. van Santen (1), Adam L. Buchsbaum (2)

(1) Lucent Technologies, Bell Labs, Murray Hill, NJ, USA
(2) AT&T Labs, Florham Park, NJ, USA

Construction of both text-to-speech synthesis (TTS) and au-tomatic speech recognition (ASR) systems involves usage of speech data bases. These data bases usually consist of read text, which means that one has significant control over the content of the data base. Here we address how one can take advantage of this control, by discussing a number of variants of "greedy" text selection methods and showing their application in a variety of examples.

Full Paper

Bibliographic reference.  Santen, Jan P. H. van / Buchsbaum, Adam L. (1997): "Methods for optimal text selection", In EUROSPEECH-1997, 553-556.