How do I generate, edit, and compile Nuance Vocalizer and Vocon user dictionaries?
Last reviewed: 12/2/2009
HOW Article ID: H120902
The information in this article applies to:
- LexiconKit 3
Summary
Nuance Vocalizer voices and VoCon 3200 recognizers support user dictionaries containing phonetic and text pronunciations.
LexiconKit 3 adds lexicon management for Nuance Vocalizer and VoCon user dictionaries and Chant Developer Workbench provides a new editing surface for the Nuance user dictionary text format.
More Information
Chant LexiconKit is comprised of software components that handle the complexities of managing and persisting word pronunciations. This allows your application to enhance the quality of speech recognition and speech synthesis and offer administrative features for maintaining word pronunciations.
Recognizers and synthesizers have their own formats for word pronunciations. LexiconKit supports the following recognizer and synthesizers and their lexicons formats:
| Recognizer or Synthesizer | Speech API |
|---|---|
| Cepstral (all languages) | Swift API |
| Microsoft SAPI 4 (all languages) | SAPI 4 |
| Microsoft SAPI 5 (all languages) | SAPI 5 |
| Nuance Vocalizer Auotmotive (all languages) | Vocalizer Auotmotive |
| Nuance Vocalizer Mobile (all languages) | Vocalizer Mobile |
| Nuance Vocalizer Network (all languages) | Vocalizer Network |
| Nuance VoCon 3200 V2 (all languages) | VoCon 3200 V2 |
| Nuance VoCon 3200 V3 (all languages) | VoCon 3200 V3 |
Editing user dictionaries can be challenging especially with the L&H phoneme format.
A new editing surface has been added to Chant Developer Workbench to edit user dictionary text format and L&H phonemes.
The intelliprompt editor has been updated with dictionary text format syntax to assist with text editing and for inserting L&H phonemes in pronunciations.
For example, the editor will automatically generate default pronunciation phonemes after typing the word followed by double backslash:
tomato // t$me&Ir6o&U