IVR

Zurich, Switzerland-based embedded speech solutions provider, SVOX, has unveiled version 9.1 of its speech recognition technology.

The new version allows for faster grapheme-to-phoneme or G2P calculation, bringing down the enrollment time for newly plugged-in music libraries or large phone books and is equipped with enhanced acoustical models of “HMMs” for German and US English to  ensure outstanding recognition results and one-shot destination entry.

 

According to SVOX (News - Alert) CEO Martin Reber, "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.”

 

In addition, the new version supports the Word Hypothesis Graph which ensures more intelligent interpretation of recognition results and with added support for new optimized algorithms, the latest version also shortens response times and lowers CPU consumption.

"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," Reber said.

The new release is immediately available to SVOX automotive and mobile customers as a part of the SVOX Automotive ASR and SVOX Mobile ASR solutions in various configurations and languages including: Canadian French, Danish, Dutch, North American Spanish, Portuguese and many others.