Speech-Enabled Media Player Applications for Mobile Devices

Nuance Communications Inc. and Gracenote recently partnered to design and promote speech-enabled solutions for digital music collections on mobile devices. The partnership comes as a next step to developing speech-enabled automotive entertainment solutions established in January 2005. The product was demonstrated at CTIA Wireless 2006 in Las Vegas, Nevada.

The gadget offers an impressive voice-activated interface to select a song, artist or playlist on MP3-enabled mobile devices. Incorporating speech capabilities from Nuance and Gracenote’s MediaVOCS phonetic database and playlist navigation, it allows users to quickly and easily find and play the music stored on their mobile devices. The built-in text-to-speech engine delivers an audio feedback assisting hands/eyes-free activation and selection verification.

As handset manufacturers enhance memory of devices, it becomes more and more difficult to browse through large music collections. Marc Theeuwes, director of mobile products at Gracenote said, “By working together, Gracenote and Nuance are making it easy for music lovers to access their favorite songs on mobile devices through speech.”

Craig Peddie, vice president and general manager for embedded speech solutions at Nuance said, “Nuance’s advanced natural language technology allows users to simply say ‘play’ and then name the song title, genre or artist.” The combination of advanced speech recognition technology and the extensive database of media information also allow users to sort and play music by recognizing nicknames.

The Nuance-Gracenote collaboration helps mobile device manufacturers to set up speech recognition technology in all kinds of MP3-enabled phones, thereby putting forth high performance and functionality to users.

Other than organizing and enjoying their mobile music collections, consumers can also use the voice command-and-control to perform other common functions.

Navigate to all media instantly:

• Play a song from a collection just by saying its name
• Instantly listen to music from specific genres, artists, albums, regions, decades or years
• Describe any combination of qualities of the music they want to hear in natural language - such as “60s Detroit Soul” to generate new mixes on the fly
• Sustain the mood of the song currently playing by asking for “More like this.”
• Get more information on a favorite song while it is playing by asking, “What is this?”

Source: GrayNote