Loquendo, the global speech-technology leader, announces the release of Loquendo ASR 7.0. This new release for Loquendo Automatic Speech Recognition offers exciting new possibilities, representing a significant step forward in terms of automatic speech interaction.

The new integration API has been completely redesigned in order to simplify integration tasks and better exploit multithread environments. System integrators can take advantage of them for integration in advanced environments such as Microsoft.Net and Java.

With Acoustic Model Composition, speech application developers can achieve greatly enhanced voice recognition performance for specific tasks. By employing either Standard or Specialized Acoustic Models, a far more flexible performance is now possible in various, diverse speech contexts: the recognition of a specific vocabulary (e.g. a string of digits, specialised command words, yes-no responses), the recognition of speech from a variety of audio channels, (e.g. VoIP, GSM / UMTS), and recognition in particular sound environments (e.g. in-car).

Loquendo ASR selects the most appropriate types of Acoustic Model, based on the grammar in use, and allows the simultaneous recognition of grammars based on different Acoustic Models.

In this major new software release, the voice recognition performance for the German language has been still further refined and improved to better support customer needs.

Loquendo ASR fully supports all standards for speech recognition, such as W3C SRGS (Speech Recognition Grammar Specification) which has had W3C recommendation since March 2004, and W3C SISR (Semantic Interpretation for Speech Recognition) which is soon to be approved by W3C. SISR enables grammar developers to use a powerful script language to validate and return semantic results from the recognition.

About Loquendo - Vocal Technology and Services
With over 30 years of R&D expertise, Loquendo is at the forefront of the global speech technologies market. Its high-quality, high-performance technologies (Loquendo TTS - text to speech, Loquendo ASR - automatic speech recognition, Loquendo Speech Server, Loquendo Speaker Verification) and platforms guarantee systems integrators the best solutions in 16 languages and 38 voices.

Currently available languages include U.S. and U.K. English, Castilian, Catalan, Mexican, Chilean and Argentinean Spanish, Italian, German, French, Greek, Mandarin Chinese, Dutch, Brazilian, Portuguese and Swedish - in both male and female voices. Many more are under development to give customers expanded reach in today's global marketplace.
From its headquarters in Turin, Italy, Loquendo deploys technologies that power millions of calls every day in telecommunications and enterprise markets throughout the world.

For more information, visit www.loquendo.com.