SVOX Releases New Version of Its Speech Recognition Solution

SVOX, a provider of embedded speech solutions, today announced the immediate availability of v9.1 of its speech recognition technology. The new release contains the following enhancements: 

• Faster G2P (grapheme-to-phoneme”) calculation; 
• New enhanced acoustical models (HMMs) for German and U.S. English; 
• Support for Word Hypothesis Graph; and
• Introduction of optimized algorithms.  

The new release is immediately available to SVOX automotive and mobile customers as a part of SVOX Automotive ASR and SVOX Mobile ASR solutions in various configurations. 

“This latest improvement of SVOX core speech recognition technology allows our automotive and mobile customers to achieve even higher recognition rates in even more difficult noise conditions,” said SVOX CEO Martin Reber. “We are now in this exciting moment where advances in the core technology and adoption rates fuel each other to produce a virtuous circle. It is especially the case in the mobile devices market where we currently see not only higher ASR and TTS penetration rates, but also significant improvements of user experience because of speech.” 

SVOX Automotive ASR and SVOX Mobile ASR Speech Recognition solutions are highly portable and available in the following languages: Canadian French, Czech, Danish, Dutch, Finnish, French, German, Greek, Italian, Japanese, Mandarin Chinese, North American Spanish, Portuguese, Spanish, U.K. English, and U.S. English. Korean, Russian, and Swedish are due to be added in 2010.