Controlling computers with your mind

/

[nik's note: Every once in a while I see something about a piece of technology that really captures the imagination, so I post it here. Thing is, this following piece of technology literally does capture the imagination.... ]


People who are completely paralyzed due to illness or trauma are getting help communicating with a new technology that connects their brains to a computer. 

Telisma annouces Thai and Malay speech recognition

/

Telisma announced the availability of two new languages: Thai and Malay, with teliSpeech Recognizer 2.0,

These new language packs are the result of the collaboration between telisma and its Malaysian partner, Nusuara.

Malay is spoken by around 250 million people in Malaysia and also in Brunei, Indonesia, Singapore, Southern Thailand, Southern Philippines and East Timor.Thai is spoken by approximately 65 million people in Thailand and also in certain regions of Cambodia, Malaysian Myanmar and Laos.
 
[click heading for more]

TravellingWave, Zi Team Up to Develop Advanced Text Messaging Using Speech Recognition

/

TravellingWave, a provider of speech-to-text software for mobile devices, and Zi Corporation, a provider of solutions for mobile search, text input and advertising, jointly announced signing a non-exclusive integration license that will enable mobile users with advanced text messaging using speech inputs.

This integration license will enable both companies to combine their technologies. TravellingWave's ‘VoicePredict’ speech-to-text software will be integrated with Zi Corporation's ‘eZiText’ and ‘eZiType’ text-prediction products, in order to facilitate mobile phone users with more advanced and accurate ‘speak and type’ text messages. This technology will open up new paths with respect to mobile messaging, search, discovery, and mobile advertisement.
 
Text prediction is a form of interactive machine translation. TravellingWave leverages speech recognition technology to enhance predictive text input. TravellingWave’s Predictive speech-to-text technology predicts words based on acoustics (speech) produced by a user in addition to the letters inputted (by the user), thereby providing quicker and simpler text prediction. [click heading for more]

Dragon NaturallySpeaking Included in New Learning Access Suite to Aid Students with Learning Difficulties

/

Nuance Communications has today announced that Dragon® NaturallySpeaking® features in the Learning Access Suite, a collection of powerful learning tools designed to make reading, writing and learning much easier. Developed in conjunction with major assistive solution providers Claro Software and Microlink PC, the Learning Access Suite is available immediately for as little as £1.10 per pupil. [click heading for more]

Nuance’s VSuite 3 Ships on Latest Katana Series Handsets by SANYO

/

Nuance’s VSuite ® software is commercially available on the latest Katana series mobile handsets by SANYO. VSuite 3 enables the voice command and control capabilities featured on the Katana® Eclipse and Katana® LX handsets.

The latest Katana series handsets by SANYO give users the power of VSuite’s innovative speech recognition application to place calls, find contacts and launch their favorite applications with simple, easy voice commands that work without any voice or user training required. All commands and responses guide users with both visual and audio cues. The Katana LX and Katana Eclipse handsets also feature Nuance’s T9® predictive text software.

Enghouse Completes Acquisition of Envox

/

Markham, Ontario, Phoenix, Arizona and Westborough, Massachusetts – (October 20, 2008) – Enghouse Systems Limited (TSX: ESL), today announced its acquisition of the business and assets of Envox Group AB. The acquisition was completed by Enghouse and certain of its subsidiaries including Syntellect Inc., for a purchase price of US$14,000,000, subject to certain adjustments. Envox’s annual revenues are approximately US$16,000,000. 

Self-service saves UK contact centres £1.6bn per year

/


“The UK Contact Centre Operational Review (6th edition - 2008)”, a recent major study of over 200 contact centres carried out by ContactBabel, has found that although only 6.5% of inbound calls are dealt with entirely through self-service, rather than a live contact centre agent, the savings to the UK contact centre industry amount to over £1.6bn per year.

Findings within the “Self-Service” chapter of the report, sponsored by Vicorp, show that of the 10.3bn calls per year that UK contact centres receive, 670m of them are dealt with entirely through automated processes. Respondents to the survey stated that on average, each call dealt with by a contact centre agent costs £2.88, whereas one dealt with by self-service costs only 43p.

“This demonstrates how organisations can benefit from self-service,” says Brendan Treacy, CEO at Vicorp.  “The business case for appropriate automation of simple and repetitive tasks is impressive and now that such services are more widely accepted by callers the savings impact is growing.” [click heading for more]

TringMe Creates Flash VoiceXML Platform

/


TringMe has announced a Flash-enabled VoiceXML platform. TringMe said, "A lot of infrastructure is required to build voice application, because of the complexity involved in building interactive voice applications and the need for optimum performance and carrier grade reliability. Even with the innovation on both voice and RIA (Rich Internet Applications) fronts, something is required to bridge the gap and make voice accessible from RIA in a simple manner effectively." 

They added, "With TringMe, we have tried to bridge this gap. With extension of our platform, TringMe opens up VoiceXML accessibility to millions of flash and web developers to easily, yet, tightly integrate voice and telephony without having to know the intricate details of call-signalling, routing, billing etc."

Developers only require Flash and Web technologies to create rich voice and telephony applications. Applications that can be developed using TringMe's Flash VoiceXML platform include speech recognition, DTMF or text-to-speech. [click heading for more]

PLS - what is it, what “gap” does it fill?

/

What PLS did is this:

  • First, it provided a single, standard XML-based language for describing pronunciations, both for speech recognizers and for speech synthesizers.
  • Second, it requires support for IPA, the International Phonetic Alphabet. This Alphabet is a standard symbol set for representing pronunciations of all the languages of the world.

With PLS it is now possible to write one lexicon document that can be used by any speech recognizer and/or any speech synthesizer that supports it. One document for all of your pronunciations, independent of your voice technology vendor.  [click heading for more]