The World Wide Web Consortium (W3C), an international consortium focused on developing Web standards, recently announced that they published new standards to help enhance the capabilities and interoperability of voice browsers and speech recognition systems. The standards include both VoiceXML (News - Alert) 2.1 and Semantic Interpretation for Speech Recognition (SISR) 1.0.

 

In support of the newly announced standards, the VoiceXML Forum, an industry organization focused on promoting and accelerating the adoption of VoiceXML-based applications, also announced enhancements to its Platform Certification Program to include certification testing for the new Web standards.

 

For those involved in speech technology, the new standards help to create voice applications that are more powerful and that enhance speech technology and voice platforms.

 

Speech technology provider Loquendo has announced their excitement with the new Web standards and said they are "looking forward to the extension of the VoiceXML Forums Certification Programme, which is also being launched in support of the new milestone."

 

"As an active participant in W3C, Loquendo firmly believes that the VoiceXML 2.1 and SISR 1.0 recommendations are essential steps forward for advancing speech applications, allowing simple and rapid upgrades, increasing portability and accelerating speech technology take-up across the globe," commented Daniele Sereno, Vice President of Product Engineering at Loquendo in a statement.

 

The new VoiceXML 2.1 standard further enhances VoiceXML 2.0 by extending dialog language to include commonly implemented features like dynamic references to grammars and scripts as well as detection of user barge-in during a prompt.

 

SISR 1.0 is also significant as it allows developers the ability to "extract and translate textual representations of words recognized by a speech recognition system and structure the results into a format convenient for processing by the speech application. For example, with SISR, one could specify the instructions for converting the spoken sentence "I want to fly from Los Angeles to Seattle." to a data structure containing "departure: LAX" and "destination: SEA", a news release noted. .

 

Loquendo recently made headlines when they announced the latest voices in their family of TTS voices, Oliver and Charlotte. The addition is a bid to better serve their customers in the North American market and rounds out their number of offerings to 20 languages and 50 voices. The new voices are Canadian French and offer the same expressive, emotional speech capabilities as other voices from Loquendo.

 

 

New Canadian French TTS Voices from Loquendo

Loquendo American Spanish TTS Voice Increases Collections Rates

Loquendo Provides Cystelcom with Text-to-Speech Capabilities

Loquendo and BySide.com Partner to Deliver Speech for Call Center and CRM Applications- Announce Special Focus on VoIP

Loquendo and BySide.com Partner to Deliver Speech for Call Center and CRM Applications- Announce Special Focus on VoIP

Loquendo Text to Speech Breathes Voice into As An Angel Virtual Assistants