25
Exploring a million hours of sounds Richard Ranft, The British Library 27 November 2014 Search Solutions 2014

Exploring a million hours of sounds Richard Ranft, The British Library 27 November 2014 Search Solutions 2014

Embed Size (px)

Citation preview

  • Slide 1
  • Slide 2
  • Exploring a million hours of sounds Richard Ranft, The British Library 27 November 2014 Search Solutions 2014
  • Slide 3
  • www.bl.uk 2 the British Librarys audio collections discovery and access finding one in a million Outline
  • Slide 4
  • www.bl.uk 3 The British Librarys audio collections originated in 1955 national collection of UK record industry selected publications from overseas radio broadcasts unpublished recordings
  • Slide 5
  • www.bl.uk 4 Subjects music spoken word environments & nature
  • Slide 6
  • www.bl.uk 5 Extent 6 million tracks from 1857 to this morning many formats 115 years of listening
  • Slide 7
  • www.bl.uk 6 Obstacles to exploring and access copyrights analogue or offline digital many non-digital tracks time-based = time consuming limited, text-based search no serendipity high expectations (c.f. iTunes, Spotify)
  • Slide 8
  • Online consumer audio services
  • Slide 9
  • opacity of audio (no freeze- frames!)
  • Slide 10
  • www.bl.uk 9 Human-led enrichment description transcription annotation category tagging rating, recommendation & review
  • Slide 11
  • Machine enrichment/search Categorisation Music genre, language/dialect detection, mood Synchronisation Score following Transcript following Identification Speaker/vocalist ID Melody recognition Query by humming/tapping Non-text browsing Map browse Timeline browse Recommendation & matching melody matching Cross-media linking Speaker/ tune matching Feature extraction Pitch, tempo, chord, time signature, rhythm Segmentation/event detection Music/speech segments Speaker/ lead instrument change Laughter, applause, emotion detection Transcription Speech-to-text Score generation
  • Slide 12
  • www.bl.uk 11 Discovery and access Sound & Moving Image Catalogue sami.bl.uk sami.bl.uk onsite listening: Appointments service SoundServer (200,000 tracks, 3% of total) off site listening: BL Sounds website (50,000 tracks, 1%) streaming downloading
  • Slide 13
  • www.bl.uk 12 Sound & Moving Image Catalogue sami.bl.uk sami.bl.uk
  • Slide 14
  • BL Sounds
  • Slide 15
  • Improving access and discovery http://sounds.bl.uk/
  • Slide 16
  • Slide 17
  • Slide 18
  • Slide 19
  • Visualisation and analysis
  • Slide 20
  • Slide 21
  • Slide 22
  • www.bl.uk 21 Current BL projects Metable software: acquire / describe UKs digital music, searching via APIs across open music databases (MusicBrainz, Decibel, Discogs) COMMA: cloud-based media analysis project with BBC http://www.bbc.co.uk/rd/projects/comma Digital Music Lab: analysing and visualising big music data collections http://dml.city.ac.uk/
  • Slide 23
  • www.bl.uk 22 Digital Music Lab example Chord detection using Chordino VAMP Plugin (Queen Mary University of London)
  • Slide 24
  • www.bl.uk 23 English conversation: At the Tobacconist's (1929) Linguaphone 78rpm shellac disc http://sounds.bl.uk/Arts-literature-and-performance/Early- spoken-word-recordings/024M-1CS0011556XX-0200V0
  • Slide 25
  • Slide 26
  • www.bl.uk 25 Thanks for listening! [email protected] http://sounds.bl.uk @soundarchive