Original title: Automatic speech segmentation using Czech TTS
Authors: Horák, Petr
Document type: Papers
Conference/Event: Czech-German Workshop on Speech Processing /9./, Prague (CZ), 1999-09-13 / 1999-09-15
Year: 2000
Language: eng
Abstract: This paper presents automatic phonetic segmentation of natural speech based on the use of a speech synthesizer and dynamic time warping (DTW) algorithm. A speech synthesizer is used to create a synthetic reference speech pattern with phonetic segmentation information (phonemes, diphones, syllables, intonation units etc.). The reference synthetic speech pattern is then used in the alignment process. The segmentation system has been developed for Czech and it uses the Czech TTS system.
Keywords: speech processing; speech synthesis
Project no.: CEZ:AV0Z2067918 (CEP), GV102/96/K087 (CEP), OC 258.10
Funding provider: GA ČR, EU COST
Host item entry: Speech Processing

Institution: Institute of Photonics and Electronics AS ČR (web)
Document availability information: Fulltext is available at the institute of the Academy of Sciences.
Original record: http://hdl.handle.net/11104/0113796

Permalink: http://www.nusl.cz/ntk/nusl-32433


The record appears in these collections:
Research > Institutes ASCR > Institute of Photonics and Electronics
Conference materials > Papers