Peachnote Massive OMR recognized 1,6 M music sheets, 500 M notes - - PDF document

peachnote
SMART_READER_LITE
LIVE PREVIEW

Peachnote Massive OMR recognized 1,6 M music sheets, 500 M notes - - PDF document

Vladimir Viro Sponsored by Ludwig-Maximilians-Universitt Munich vladimir@viro.name Peachnote Massive OMR recognized 1,6 M music sheets, 500 M notes multiple collections: IMSLP, Library of Congress, Duke, more to come poly-OMR: virtualized


slide-1
SLIDE 1

API All functionality and data exposed to the world N-gram data released under CC-By License

Sponsored by

Technologies Massive OMR Music Ngram Viewer and Search Engine Vladimir Viro

Ludwig-Maximilians-Universität Munich vladimir@viro.name

Peachnote

Usage

recognized 1,6 M music sheets, 500 M notes multiple collections: IMSLP, Library of Congress, Duke, more to come poly-OMR: virtualized workflow supports all publicly available OMR packages Hadoop and HBase for scalable storage, computation and serving VMware and AutoIt for running OMR software Google App Engine and GWT for security and scalability of the frontend Google Analytics for collecting and querying usage data Search for scores containing melodies and chord sequences with or without rhythm Simple inverted index with billions of entries, but highly compressed(!) thanks to HBase Different query entry modes Melody search engine at IMSLP 500-1000 daily visitors from over 170 countries More than 300 users visited more than 100(!) times each Usage data used to improve search results

  • 69 5 -12_5_4 -12_3 13 0 4 -9:1870 : 1

69 5 -15 3 7 3 -13 3:1870 : 23 69 5 -19 9 -4_11 -16_7:1871 : 2

  • Sharing

Have an algorithm working with symbolic music data? Let it shine on the largest symbolic music data set! See a way of enriching your application with scanned sheet music or statistics derived from it? Please get in touch!

http://www.peachnote.com/{api,datasets}.html

peachnote.com

slide-2
SLIDE 2

Peachnote

  • Melody search for digitized music scores
  • Music N-Gram Viewer
  • Embeddable Score Viewer
  • Collaborative score annotation system
  • 170,000 users since launch of the N-Gram Viewer
  • 1,000,000 users from 200 countries a month for the

new Score Viewer and annotation platform

slide-3
SLIDE 3

N-Gram Viewer and Search Engine

slide-4
SLIDE 4

Score Viewer

slide-5
SLIDE 5

User base

slide-6
SLIDE 6

User base

slide-7
SLIDE 7

Outlook

More users

  • Music libraries around the world
  • Broadcasting organizations
  • Publishers
slide-8
SLIDE 8

Technologies

  • Google App Engine, Google Storage
  • Amazon SQS, EC2, S3
  • Virtualization
  • Hadoop, HBase
slide-9
SLIDE 9

Workloads

  • OMR – optical music recognition
  • commercial software – in VMs
  • own data-mining algorithms – in Hadoop
  • Data mining
  • Evolution of music
  • Search log data
  • Other CPU-intensive IR tasks
  • syncrhonizing audio and video with scores