Analysis Report (Full Draft)

Analysis Report (Full Draft) - 1976 N 110 W Apt. 128 Provo,...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon
1976 N 110 W Apt. 128 Provo, UT 84604 October 25, 2010 Professor Carter-Hadley English Composition Department Brigham Young University Provo, UT 84604 Dear Professor Carter-Hadley, The title of this report is Music Retrieval Systems: A General Public Service Product. The purpose of this report is to determining the feasibility of implementing a large scale Music Retrieval System for the general public that allows people to find songs based on audio input. My audience is mainly corporate managers and investors looking for an assurance that their investment into such a project would yield successful results. My methods were mainly to research the existence of solutions that is capable of recognizing tunes based on audio inputs and determining their practicality and then to see if it was feasible to scale the solution so that it can process enormous amounts of music and service the large population of the general public. It turns out that I have been living under a rock and commercial solutions already exist. Nevertheless, I proceeded to search out competitive solutions that would also be feasible and concluded that the combination of various feasible approaches would yield a better MIR system. Sincerely, Kieran Tsai Abstract It is now the norm to search for items using text based services such as Google. However, when it comes to searching music where you lack the contextual information such as the title of the song, the name of the artist, how would you search for it? Often people find this frustrating; especially when they remember how the tune goes but are not capable of identify what it is. In this analysis, different approaches have been explored to determine whether the Music Information Retrieval System built is
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
capable at recognizing tunes given audio input. Namely, the Query by Example technique employed by Shazam Entertainment has successfully accomplished this task, and that the Query by Humming only lags behind a little in terms of practicality. Such MIR systems have already been commercialized using a Master Slave model and a cluster of computers for deployment which scales really well with large databases and user input. Hence, MIR by audio input is no longer a dream, but a reality. Keywords: Music Information Retrieval Systems, Tune Recognition, Melody Input.
Background image of page 2
I NTRODUCTION Have you ever had a tune that got stuck in your head but didn’t know the name of it? Have you ever wanted to look up a piece of music and had to reference Opus numbers which were hard to remember? Well, look no further as a scalable solution is here and opportunities await us in developing, implementing and deploying a terrific Music Information Retrieval System. Several companies and research groups have attempted different algorithms in recognizing melodies, tunes from all sorts of different musical databases. In the UK, a company by the name of Shazam Entertainment has already deployed a service based on Query by Example (QBE). Another research group has also succeeded in implementing a Tune
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 4
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/25/2011 for the course ENGL 316 taught by Professor Liacarterhadley during the Fall '10 term at BYU.

Page1 / 9

Analysis Report (Full Draft) - 1976 N 110 W Apt. 128 Provo,...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online