Loquendo, the leading innovator in speech technology, today announced the new release of Loquendo ASR, with two significant developments: acoustic models for the Aurora Distributed Speech Recognition (DSR) now in UK English and German, and acoustic models for the French language now with greatly enhanced accuracy. These important steps forward for Loquendo ASR render it ever more accurate and give it ever more reach in the global market place.

In response to calls from many of our customers, Loquendo has now developed acoustic models in UK English and German for the ETSI Aurora Distributed Speech Recognition, fully compliant with the ETSI ES 202 050 and ES 202 212 specifications. Loquendo ASR is now able to process advanced (noise-robust) front-end signal feature streams for DSR/Aurora systems. This avoids degradations caused by both the voice encoding process and by the effects of transmission errors. It also considerably increases robustness to background noise. DSR/Aurora front-end is being adopted by the world's top mobile vendors.

Developments have also been made for the French language acoustic models: these acoustic-phonetic models are based on an optimized version of the set of phonetic units. The speech corpora used for the training of the acoustic models were processed by a tool able to discard any recorded material displaying defects (e.g. poor transcription, distortion, background noise). These new models achieve significantly improved Semantic Accuracy over the set of built-in grammars on which they were evaluated.

Loquendo ASR is next-generation Speech Recognition Technology, with a well proven capacity to create automated voice solutions that are accurate, flexible and robust - even in the noisiest of environments. The wide range of Loquendo ASR languages is now also available in Argentinean, Brazilian, Castilian Spanish, Catalan, Chilean, Dutch, French, German, Greek, Italian, Mexican, Portuguese, Swedish, U.K. and U.S. English.

About Loquendo - Vocal Technology and Services
With over 30 years cutting-edge R&D experience, global speech-technologies leader Loquendo provides all the technologies required for creating the ultimate speech-interaction solutions. Loquendo's best-in-breed technologies - Loquendo TTS, Loquendo ASR, Loquendo Speaker Verification - and the VoxNauta Platform enable integrators to rapidly and easily create best-in-breed solutions in 17 languages.
Currently available languages include U.S. and U.K. English, Castilian, Catalan, Mexican, Chilean, Argentinean, American 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.

Loquendo is a Telecom Italia company headquartered in Turin, Italy. It is the leading technological partner for integrators in the speech solutions field throughout Europe, the U.S. & Latin America. Many enterprises and carriers worldwide have recognized the Loquendo difference, and Loquendo solutions currently automate millions of calls every day.

For more information about Loquendo, and to hear demos of all the Loquendo voices, go to www.loquendo.com.