| 1 | | Prosody Specification Support |
| | 1 | |
| | 2 | == Support for Prosody Specifications == |
| | 3 | |
| | 4 | MARY TTS support explicit prosody specification using 'prosody' element as described in W3C Speech Synthesis Markup Language (SSML) recommendations; and the different attributes in 'prosody' element like 'rate', 'pitch' and 'contour' are used as specifications to modify predicted phone durations and pitch contour before passing them to synthesizer. |
| | 5 | |
| | 6 | Example 1: |
| | 7 | |
| | 8 | {{{ |
| | 9 | <?xml version="1.0" encoding="UTF-8" ?> |
| | 10 | <maryxml version="0.4" |
| | 11 | xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" |
| | 12 | xmlns=" http://mary.dfki.de/2002/MaryXML" |
| | 13 | xml:lang="en-US"> |
| | 14 | <p> |
| | 15 | <prosody rate="fast" pitch="+10%" contour="(10%,low)(50%,-20%)(80%,+10%)(100%,+5st)"> |
| | 16 | Welcome to the world of speech synthesis! |
| | 17 | </prosody> |
| | 18 | </p> |
| | 19 | </maryxml> |
| | 20 | }}} |
