Removing linear phase mismatches in concatenative speech synthesis.

Many current text-to-speech (TTS) systems are based on the concatenation of acoustic units of recorded speech. While this approach is believed to lead to higher intelligibility and naturalness than synthesis-by-rule, it has to cope with the issues of concatenating acoustic units that have been recor...

Volledige beschrijving

Bibliografische gegevens
Gepubliceerd in:	IEEE Transactions on speech and audio processing 9, 3 (2001).
Hoofdauteur:	Stylianou, Y.
Formaat:	Artikel
Taal:	English
Onderwerpen:	AT&T Labs. HNM. TTS system. Acoustic units concatenation. Center of gravity. Concatenated speech frames. Concatenative speech synthesis. Differentiated phase data. Harmonic plus noise model. Linear phase mismatch removal. Output speech quality. Phase spectra processing. Recorded speech. Signal processing. Speech database. Speech intelligibility. Synchronization. Text-to-speech systems.