Changes between Version 2 and Version 3 of 4.1.0


Ignore:
Timestamp:
09/01/10 15:49:19 (14 years ago)
Author:
masc01
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • 4.1.0

    v2 v3  
    55 
    66== New features for expressive TTS == 
    7  * Prosody control for HMM-based voices. Using the SSML <prosody> tag, it is now possible to control the intonation generated for HMM-based voices from markup. Of particular interest is the "contour" attribute, which allows you to change the shape of the intonation curve. For details and examples, see ... 
    8  * Expressive vocalizations in certain unit selection voices. MaryXML now supports a new <vocalization> tag, with which you can request the generation of non-verbal or para-verbal expressions as they are often produced by the listener in a conversation, such as "yeah", "m-hm", laughter, sigh, etc. For details and examples, see ... 
     7 * '''Prosody control for HMM-based voices'''. Using the SSML <prosody> tag, it is now possible to control the intonation generated for HMM-based voices from markup. Of particular interest is the "contour" attribute, which allows you to change the shape of the intonation curve. For details and examples, see ... 
     8 * '''Expressive vocalizations''' in certain unit selection voices. MaryXML now supports a new <vocalization> tag, with which you can request the generation of non-verbal or para-verbal expressions as they are often produced by the listener in a conversation, such as "yeah", "m-hm", laughter, sigh, etc. For details and examples, see ... 
    99 
    1010== New voices == 
     11 * For British English, we release HMM-based versions of the four voices Poppy, Spike, Obadiah and Prudence. 
     12 
     13[[BR]] 
    1114== Bugfixes and other improvements == 
     15 * Faster startup times. MARY 4.1.0 starts up to twice as fast as MARY 4.0.0 and needs about 30% less physical memory, due to the use of memory mapping for unit selection voices. 
     16 *