Changes between Version 6 and Version 7 of VocalizationSynthesis


Ignore:
Timestamp:
12/10/10 12:42:20 (13 years ago)
Author:
sach01
Comment:

--

Legend:

Unmodified
Added
Removed
Modified

  • VocalizationSynthesis

    v6 v7  
    22== Synthesis of vocalizations using MARY TTS == 
    33 
    4    MARY supports synthesis of vocalizations with following MARYXML (WORDS input type) requests.  
     4 
     5Listener vocalizations play an important role in communicating listener intentions while the interlocutor is talking. They include non-linguistic vocalizations like ''uh-huh, mhm, (laughter),'' and ''(sigh)'' as well as verbal response tokens such as ''yes, right, really,'' and ''absolutely''. To communicate different intentions, a synthesiser should be capable of generating a broad range of vocalisations with different kinds of acoustic properties. In multimodal human-computer interaction, the ability of systems to generate vocal listener behavior is an important requirement for generating affective interaction. This page aims to provide examples to synthesize vocalizations using MARY speech synthesis framework.  
     6 
     7MARY supports synthesis of vocalizations with following MARYXML (WORDS input type) requests.  
    58 
    69 
    … …  
    2326 
    2427 
    25  Example: 
     28 Example 2.1: 
    2629 
    2730  {{{ 
    … …  
    3538  }}} 
    3639 
     40 Example 2.2: 
     41 
     42  {{{ 
     43<maryxml version="0.5" xmlns="http://mary.dfki.de/2002/MaryXML" xml:lang="en-GB"> 
     44<voice name="dfki-poppy"> 
     45<p> 
     46<vocalization name="yeah" meaning="agreeing" intonation="mid" voicequality="modal"/> 
     47</p> 
     48</voice> 
     49</maryxml> 
     50  }}} 
     51 
    3752See also the interactive documentation at http://mary.dfki.de:59125/documentation.html#vocalizations 
    3853