Groove Extraction of Phonographic Records

  • Sylvain Stotzer
  • Ottar Johnsen
  • Frédéric Bapst
  • Rolf Ingold
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3872)


Historical sound documents are of high importance for our cultural heritage. The sound of phonographic records is usually extracted by a stylus following the groove, but many old records are in such bad shape that no mechanical contact is possible. The only way to read them is by a contactless reading system. A phonographic document analysis system was developed using an optical technique to retrieve the sound from old records. The process is straightforward: we take a picture of each side of the disc using a dedicated analog camera, we store the film as our working copy, and when needed, we scan the film and process the image in order to extract the sound. In this paper, we analyze the imaging issues and present the algorithm for extracting the groove position and therefore the sound of the records.


Edge Detection Motion Blur Record Picture Luminance Transition Groove Position 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Bradley, K., et al.: Guidelines on the Production and Preservation of Digital Audio Objects. In: IASA – TC 2004 (2004) ISBN 87-990309-1-8Google Scholar
  2. 2.
    Poliak, J., Robert, P., Goy, J.: Optical Fibre Turntable for Archive Records. In: Proceedings of the 92nd Convention AES, Vienna, Austria (1992)Google Scholar
  3. 3.
    Fadeyev, V., Haber, C.: Reconstruction of Mechanically Recorded Sound by Image Processing, J. Audio Eng. Soc. 51(12), 1172–1185 (2003)Google Scholar
  4. 4.
    Cavaglieri, S., Johnsen, O., Bapst, F.: Optical Retrieval and Storage of Analog Sound Recordings. In: AES 20th International Conference, Budapest (2001)Google Scholar
  5. 5.
    Stotzer, S., Johnsen, O., Bapst, F., Sudan, C., Ingold, R.: Phonographic Sound Extraction Using Image and Signal Processing. In: IEEE Proceedings 2004. ICASSP, vol. 4, pp. 289–292 (2004)Google Scholar
  6. 6.
    Stotzer, S., Johnsen, O., Bapst, F., Milan, C., Ingold, R.: Phonographic Sound Extraction using Photography and Signal Processing. In: Digital Signal Processing. Elsevier, Amsterdam (to be published)Google Scholar
  7. 7.
    Elder, J.: The Visual Computation of Bounding Contours. PhD Thesis, Mc Gill University, Dept. of Electrical Engineering (1995)Google Scholar
  8. 8.
    Temmer, S.F. (ed.): Disk Recording (Anthology), vol. 1. Audio Engineering Society, New York (1980)Google Scholar
  9. 9.
    Canny, J.: A computational approach to edge detection. IEEE Trans. on Pattern Analysis and Machine Intelligence 8(6), 679–698 (1986)CrossRefGoogle Scholar
  10. 10.
    Pentland, A.P.: A new sense for depth of field. IEEE Tran. PAMI 9(4), 523–531 (1987)Google Scholar
  11. 11.
    Esquef, P., Biscainho, L.W.P., Diniz, P.S.R., Freeland, F.P.: A double threshold-based approach to impulsive noise detection in audio signal. In: Proc. X European Signal Processing Conf (EUSIPCO 2000), Tampere, Finland, pp. 2041–2044 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sylvain Stotzer
    • 1
    • 2
  • Ottar Johnsen
    • 1
  • Frédéric Bapst
    • 1
  • Rolf Ingold
    • 2
  1. 1.University of Applied Sciences of FribourgFribourgSwitzerland
  2. 2.DIVA Group, DIUFUniversity of FribourgFribourgSwitzerland

Personalised recommendations