Using Various Types of Multimedia Resources to Train System for Automatic Transcription of Czech Historical Oral Archives

  • Josef Chaloupka
  • Jan Nouza
  • Michaela Kucharova
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8158)


Historical spoken documents represent a unique segment of national cultural heritage. In order to disclose the large Czech Radio audio archive to research community and to public, we have been developing a system whose aim is to transcribe automatically the archive files, index them and make them searchable. The transcription of contemporary (1 or 2 decades old) documents is based on the lexicon and statistical language model (LM) built from a large amount of recent texts available in electronic form. From the older periods (before 1990), however, digital texts do not exist. Therefore, we needed a) to find resources that represent language of those times, b) to convert them from their original form to text, c) to utilize this text for creating epoch specific lexicons and LMs, and eventually, d) to apply them in the developed speech recognition system. In our case, the main resources included: scanned historical newspapers, shorthand notes from the national parliament and subtitles from retro TV programs. When converted into text, they allowed us to built a more appropriate lexicon and to produce a preliminary version of the transcriptions. These were reused for unsupervised retraining of the final LM. In this way, we significantly improved the accuracy of the automatically transcribed radio news broadcast in 1969-1989 era, from initial 83 % to 88 %.


historical audio archives speech-to-text transcription OCR lexicon building machine learning 


  1. 1.
    Hansen, J.H.L., Huang, R., Zhou, B., Seadle, M., Deller, J.R., Gurijala, A.R., Kurimo, M., Angkititrakul, P.: SpeechFind: Advances in Spoken Document Retrieval for a National Gallery of the Spoken Word. IEEE Trans. on Speech and Audio Processing 13(5), 712–730 (2005)CrossRefGoogle Scholar
  2. 2.
    Ordelman, R.J.F., de Jong, F.M.G., Huijbregts, M.A.H., van Leeuwen, D.A.: Robust audio indexing for Dutch spoken-word collections. In: 16th Int. Conference of the Association for History and Computing. Humanities, Computers and Cultural Heritage, Amsterdam, pp. 215–223 (2005)Google Scholar
  3. 3.
    Christel, M.G., Stevens, S.M., Maher, B.S., Richardson, J.: Enhanced exploration of oral history archives through processed video and synchronized text transcripts. In: Proceedings of the International Conference on Multimedia, pp. 1333–1342. ACM (2010)Google Scholar
  4. 4.
    Byrne, W., et al.: Automatic recognition of spontaneous speech for access to multilingual oral history archives. IEEE Trans. Speech Audio Process. 12(4), 420–435 (2004)CrossRefGoogle Scholar
  5. 5.
    Goldman, J., et al.: Accessing the spoken word. International Journal on Digital Libraries 5(4), 287–298 (2005)CrossRefGoogle Scholar
  6. 6.
    Nouza, J., Blavka, K., Bohac, M., Cerva, P., Zdansky, J., Silovsky, J., Prazak, J.: Voice Technology to Enable Sophisticated Access to Historical Audio Archive of the Czech Radio. In: Grana, C., Cucchiara, R. (eds.) MM4CH 2011. CCIS, vol. 247, pp. 27–38. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  7. 7.
    Nouza, J., Blavka, K., Zdansky, J., Cerva, P., Silovsky, J., Bohac, M., Chaloupka, J., Kucharova, M., Seps, L.: Large-scale processing, indexing and search system for Czech audio-visual cultural heritage archives. In: IEEE 14th International Workshop on Multimedia Signal Processing (MMSP), pp. 337–342 (2012)Google Scholar
  8. 8.
    Nouza, J., Blavka, K., Cerva, P., Zdansky, J., Silovsky, J., Bohac, M., Prazak, J.: Making Czech Historical Radio Archive Accessible and Searchable for Wide Public. Journal of Multimedia 7(2), 159–169 (2012)CrossRefGoogle Scholar
  9. 9.
    Czech Parliament webpages,
  10. 10.
    Kneser, R., Ney, H.: Improved backing-off for m-gram language modeling. In: Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Detroit, pp. 181–184 (1995)Google Scholar
  11. 11.
    Nouza, J., Cerva, P., Silovsky, J.: Dealing with Bilingualism in Automatic Transcription of Historical Archive of Czech Radio. In: Petrosino, A., Maddalena, L., Pala, P. (eds.) ICIAP 2013 Workshops. LNCS, vol. 8158, pp. 238–246. Springer, Heidelberg (2013)Google Scholar
  12. 12.
    Cerva, P., Palecek, K., Silovsky, J., Nouza, J.: Using Unsupervised Feature-Based Speaker Adaptation for Improved Transcription of Spoken Archives. In: Proc. of Interspeech 2011, Florence, pp. 2565–2568 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Josef Chaloupka
    • 1
  • Jan Nouza
    • 1
  • Michaela Kucharova
    • 1
  1. 1.Institute of Information Technology and ElectronicsTechnical University of LiberecLiberecCzech Republic

Personalised recommendations