Innovative Speech Applications for Mobile Phones

Nuance Communications, Inc., has announced new speech applications for device manufacturers to enable voice-activated dialing, voice control of mobile device functionality and audio output of SMS messages.

The new applications SpeechPAK Driver Mode and SpeechPAK SMS Reader bundle speech technology, user interface design and development tools. This package enables hands-free and eyes-free use of mobile devices for improved convenience, safety and accessibility.

Craig Peddie, vice president and general manager said, “We’re offering the industry’s most complete suite of speech-based applications for mobile devices so that companies can quickly and easily integrate speech technology into their platform and bring it to market.”

SpeechPAKs will offer more convenient control of handset features, by allowing users to quickly access the advanced features of a mobile phone that may otherwise be lost deep within menus. With these functions, users can navigate a mobile phone’s menus and contact lists without looking at the keypad or screen, and they can stay focused on the road while making and receiving calls and text messages, thus offering a safer way to use mobile phones while driving.

The current suite of SpeechPAK applications includes the following functionality:

• Voice-Activated Dialing: enables users to control various handset features, including name and number dialing by voice. Speech input is confirmed with audio feedback using natural-sounding text-to-speech (TTS). 
• SMS Reader: delivers natural-sounding voice readout of SMS messages. 
• Driver Mode: combines TTS and speech recognition technologies to enable a driver to listen to incoming SMS messages, hear the name of callers and have access to spoken alerts of low battery or roaming status. The user can also take advantage of the voice-activated dialing capabilities in an eyes-free mode to make calls.

Additional SpeechPAKs are planned to provide scalable SMS dictation capabilities with continuous learning and intuitive error correction, as well as speech-activated MP3 to enable full voice control of media applications.

Source: 3GSM World Congress 2006, Barcelona, Spain