Looking to put together a music discovery engine based on [url removed, login to view] open source.
Basically i will have new artists and new songs uploaded to my server. The user searches for an artist that sounds like "Madonna" or a song that sounds like "Like a Prayer" and using acoustic fingerprinting, the discovery engine looks at the songs of the unknown artists and offers songs that sound like or are acoustically similar to "Madonna" or "Like a Prayer" for example. This will be a a new music discovery engine:
• Creates playlists/mixes based on the named artist, album or track
• Utilizes song fingerprints and acoustic tags
• Recommends similar music, based on acoustic analysis
• Includes parameters based on preference, variety, and genre
• Incorporates metadata-reliant parameters for richer results
• Applies shuffle algorithms to generate different mixes
• Provides acoustic relationships between tracks, albums and other entities
• Supports large music collections
Application is based on the open source of [url removed, login to view] and [url removed, login to view]
[url removed, login to view]
MusicBrainz is a user-maintained community music metadatabase. Music metadata is information such as the artist name, the album title, and the list of tracks that appear on an album. MusicBrainz collects this information about music and makes it available to the public so that music players can retrieve information about the music that is playing. For instance, most audio CDs do not contain the name of the artist, album, or a listing of the tracks. A music player can use the digital characteristics of an audio CD to look up the correct metadata and show it to the user during playback.
MusicBrainz also takes this concept one step further in applying it to digital audio files like MP3 files and Ogg Vorbis files. The metadata contained in these files is often incorrect or missing altogether. If this data is not present or correct, it makes it difficult for users to find the music they wish to play. Many MP3 lovers have a huge collection of MP3 files but often have a hard time finding the music to which they want to listen. The MusicBrainz solutions for this are the WindowsTagger, iEatBrainz, and the Picard Tagger--Windows, MacOS X, and Python applications that use AcousticFingerprints (TRMs) to semi-automatically identify tracks in your music collection and then write consistent and accurate metadata to your music files.
The MusicBrainz web site provides a catalog of music metadata; MusicBrainz only provides the data about the music. MusicBrainz users can browse and search this catalog to examine what music different artists have published and how those artists relate to each other to discover new music. The music metadata and its ability to uniquely identify music will also enable non-ambiguous communication about music, and will allow the Internet community to discover new music without any of the bias introduced by marketing departments of the recording industry.
[url removed, login to view]
MusicDNS is the largest single dataset of acoustic fingerprints in the world with more than 16 million individual tracks identified.
With the Open Fingerprint client-code, tracks can be identified consistently against the MusicDNS dataset, and new tracks are easily added. Currently, MusicDNS and the Open Fingerprint Architecture are being used to:
• identify duplicate tracks, even when the metadata is different, MusicIP identifies the master recording.
• fix metadata
• find out more about tracks by connecting to MusicBrainz- the worlds largest music metabase community
Basically I am building a music site with thousands of unknown bands so i am looking to develop a music discovery engine that can help users discover new unknown artists by searching for artists that they like and songs that like and then the discovery engine gives them artists that acoustically sound like the established songs/artists they are looking for.
Payment will be done in paypal - 25% down 75% upon completion.
9 freelancere byder i gennemsnit $4011 for dette job
Dear Project Owner, We believe that our company LightIdeas has very good chances to succeed in project delivery if we qualify and get awarded. I am looking forward to your feedback. Thank you. LightIdeas