论文信息 - High-quality message-to-speech generation in a practical application

High-quality message-to-speech generation in a practical application

This chapter describes the use of concatenation of prerecorded words to generate spoken messages in a practical application. This simple technique can lead to quite acceptable results if the utterances are provided with appropriate prosody using a waveform manipulation technique.

Jan-Roelof de Pijper

[1] Angelien Sanderman,et al. On the perceptual strength of prosodic boundaries and its relation to suprasegmental cues , 1994 .

[2] de Jr Jan-Roelof Pijper,et al. APPEAL: A multimedia environment for adaptive learning , 1994 .

[3] Jacques M. B. Terken. Synthesizing natural-sounding intonation for Dutch: rules and perceptual evaluation , 1993, Comput. Speech Lang..

[4] Eric Moulines,et al. A diphone synthesis system based on time-domain prosodic modifications of speech , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[5] Eric Moulines,et al. Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones , 1989, Speech Commun..

[6] Angelien Sanderman. How can prosody segment the flow of (synthetic) speech? , 1994, SSW.

[7] Rpg Rene Collier,et al. Prosodic phrasing at the sentence level , 1995 .