Veridict Automatic Speech Recognition

Veridict Daytona Automatic Speech Recognition (ASR) is the next-generation speech recognition technology for speech-enabled applications and services.

It is a robust, scalable speech recognition technology using the same core engine for server, multimedia and field applications, e.g. for in-vehicle deployments. The recognizer is speaker-independent and reliably recognizes large-scale vocabulary continuous speech, even in noisy environments.

Daytona is available for the Microsoft Windows platforms, including Windows 7, Windows XP, Server 2003/2008,  XP Embedded and clients for Windows Mobile Smartphones.

Built to support all major open ASR standards and file formats. Support for several language model formats, including W3C SRGS grammar and various n-gram model formats, including SRILM.  SAPI and System.Speech is supported.

Speech Software Development Kit supporting the Microsoft.NET platform with simple managed APIs in any .NET language, e.g. C# and VB.NET. The software allows integrators the freedom to create products and services that are user-friendly and as complex as they want them to be, in terms of vocabulary size and interaction flexibility.

The Daytona ASR perfectly fits the requirements of each and every application scenario - however complex. Support for speaker-independent continuous speech with very large vocabularies.

In addition, the technology provides support for Acoustic Model Adaptation. This enables further enhancements in recognition accuracy by adapting to the specific criteria, e.g. the acoustic environment, individual speakers or channel adaptation.

 For additional information, please contact us at: info