Gracenote MediaVOCS®
Gracenote MediaVOCS is the industry’s most intuitive speech-based digital management, discovery and enjoyment solution. Through this solution, users can navigate, manage, explore and play their digital media collections in the car and beyond using voice commands. With MediaVOCS, Gracenote applies its expertise in media recognition, navigation and automatic playlist creation to speech recognition (ASR) and text-to-speech (TTS) technology.
Hands-free Access to Music and Media
MediaVOCS integrates seamlessly with other Gracenote technologies for additional enjoyment, such as Gracenote MusicID® for music identification of local content and Gracenote’s Playlist Plus™ for access and management to externally connected devices such as an MP3 player. Device manufacturers can quickly deploy advanced speech-based media control features in a variety of digital devices, and MediaVOCS-enabled products provide entertainment fans with hands-free access to their entire media collections in the car, at home, or on the go.
Pronunciation and Phonetics
ASR and TTS are limited when it comes to music. While ASR and TTS technologies have been longstanding well-developed parts of the digital landscape, neither ASR or TTS are designed to address the complexities of music. It's difficult for these technologies to recognize artist names, album names, and especially nicknames or alternate names or pronunciations. MediaVOCS addresses the limitations of existing ASR and TTS solutions by using a proprietary database of phonetic transcriptions for official and alternate artist, album, and genre names. Standard speech technologies cannot consistently recognize or pronounce common artist, album, and genre names. These often contain a variety of non-standard terms, including multiethnic names, abbreviations, special characters, upper case letters, numbers, nicknames, and invented words that defy the default pronunciation and language rules built into these systems.
Finding the Music
MediaVOCS enables voice commands and provides an alternative way to use devices with more accuracy than typical speech solutions. For example, traditional graphical user interfaces in devices that have small displays and limited manual control options become impractical when scrolling for an artist in a 5,000-piece collection while driving a car.
MediaVOCS enables consumers to use voice commands to:
- Instantly navigate to an artist, album, or genre
- Play any individual artist, album or genre in a collection, just by saying its name
- Create new instant mixes on-the-fly
- Create More Like This™ instant playlists to stay in the mood of the song currently playing
- Describe any combination of qualities of the music they want to hear in natural language - such as "60's Detroit Soul" to generate new "On-The-Fly" mixes
- Get information on artists and albums
- Get more information on a new song currently playing by simply asking, "What is this?"
Phonetic Transcription Data
MediaVOCS provides phonetic transcription data in the language of origin for a more natural user experience, and provides the transcription data in multiple languages, supporting global deployments. MediaVOCS provides the essential and critical phonetic transcription data required to not only recognize and pronounce names and terms correctly, but also to recognize common user mispronunciations:
Artist names:
"Sade" (pronounced "shah-DAY"), "Björk" (pronounced "bee-YORK"), 311 (pronounced "three-eleven", not "three-one-one"); "Aaliyah" (pronounced "Uh-LEE-uh"); "Chic" (pronounced "sheek")
Album and song titles:
"Aja" (pronounced "A-zjyah"), "808 State" (pronounced "eight-oh-eight state"), "The Girl from Ipanema" (the last word pronounced "ee-puh-NEE-muh").
Genre names:
Merengue (pronounced "muh-RANG-gay")
Phonetic Variants
Music fans from around the world have their own way of pronouncing a band or artist's name. Phonetic variants enable recognition of a wide range of pronunciations.
Artist names:
Gloria Estefan (alternate pronunciations "eh-STAY-fan" or "EH-stah-fan")
Album and song titles:
D'yer Mak'er ("dja-MAY-ka" or "DI-yer-MAK-er");
Genre names:
Quebecois ("ke-be-KWAH" or "KWE-be-koy").
Additional Artist, Album, and Genre Alternate Names
Elvis Presley is known by more names than just Elvis Presley. He's also "The King". MediaVOCS accounts for many nicknames and aliases coined for iconic artists and bands.
Artist Nicknames:
"The Fab Four" (The Beatles), "The King" (Elvis Presley), "Ol' Blue Eyes" (Frank Sinatra), "The Stones" (The Rolling Stones)
Artist Short Names:
"Dylan" (Bob Dylan), "Aretha" (Aretha Franklin), "Mozart" (Wolfgang Amadeus Mozart)
Artist Name Abbreviations:
"CCR" (Creedence Clearwater Revival), "BTO" (Bachman Turner Overdrive)
Album Title Nicknames:
"Zep Four", "Zoso", "Black Dog", and "Runes" (for the untitled fourth Led Zeppelin album), "The White Album" (The Beatles self-titled album).
Genre Abbreviation:
" R&B" (for "Rhythm and Blues")
Enhanced Voice Commands to Manage, Enjoy, and Discover music
In just a few words you can play your favorite artists, play your favorite album, or even create an entire automatic playlist to fit your mood. MediaVOCS works with Gracenote MusicID®, Playlist™, and Playlist Plus™, to enable voice control of the most popular Gracenote functionality.
MusicID and Playlist Plus
Identification:
"What is This?" "Artist Name," "Album Name," or "What Year Is This From?"
Playback:
"Play Artist 'Bowie'," "Play Song 'Fame'," "Pause," or "Repeat"
Playlist™ and Playlist Plus
Automatic Playlist:
"More Like This," "More Like This Artist," "More From This Place," "More From This Year," "Play 50's Jazz," or "Play Female Duos"
Link to Commerce
Link Services:
"Buy Ringtone," "Read Review," "Download Album," "Buy Ticket"
Navigation
Browse Services:
"Browse Songs From 1982," "Browse French Artists," or "Browse Blues Artists"
