Acoustic Models

Robust Affordable Speech Recognition

• $199 per channel perpetual license
• Acoustic models for 4 major languages:

- American English	- Chinese Mandarin
- Australian English	- Indian English

   • SRGS (XML & ABNF) grammar format
   • MRCP (v1 & v2) platform integration
   • Scalable architecture & load balancing
   • Asterisk and FreeSWITCH support
   • Linux and Windows installation

Vestec ASR is designed to support all major spoken languages. In order to conduct speech recognition in a particular language, the customer needs to install acoustic model for that language (if available).

We currently offer acoustic models for the following 4 languages:

• American English	• Chinese Mandarin
• Australian English	• Indian English

Work is underway on acoustic models for several other Asian and European languages, including: Arabic, Dutch, French, German, Hindi, Italian, Portuguese, Spanish, and Turkish.

Acoustic models are not included in the retail price of ASR engine. They need to be licensed separately at $20 per language per port.