| Architecture |
Single
Client |
| Simultaneous
Channels |
Single
Channel |
| Memory
Requirements |
RAM: 4 MB
ROM: 4 MB per language |
| Type
of Technology |
Neural networks + Continuous Density
Hidden Markov Models
|
| Sampling
Rate |
8/16 KHz |
| CPU
requirements |
Xscale,
ARM9, ARM11, X86
CPU 400 MHz min. |
| Platforms |
Windows
Mobile 6.0 (all editions), Windows Mobile
5.0 (all editions), Pocket PC 2003, CE 5.0,
CE.NET 4.2, Windows XP Embedded and TabletPC
ed., Linux |
| Interfaces |
Loquendo
API (C/C++) |
| Supported
Languages |
American
English, Canadian French, Brazilian
Portuguese, Argentinian Spanish, Chilean
Spanish, Mexican Spanish, British English,
Castilian Spanish, Catalan, Valencian, Galician*,
Dutch, French, German, Greek, Italian, Polish,
Portuguese, Swedish,Turkish, Russian*
(* available during 2008) |
| Standards
Supported |
JSGF
(Java Speech Grammar Format)
W3C SRGS 1.0 (ABNF Form) |
| Key
Features |
• Speaker
Independent
• Open Vocabulary
• Noise robustness (e.g. in-car, wireless,
etc.)
• N-Best Decoding
• Confidence Scores at sentence and
word level
• Tunable Voice Detection sensitivity
• Enhanced Barge-In functionalities
• Grammar handling and fast grammar
compilation on the fly
• Voice enrolled grammars
• Natural Language Processing
• Acoustic model composition |
|
|
 |
|