Advertisement

Online TV Captioning of Czech Parliamentary Sessions

  • Jan Trmal
  • Aleš Pražák
  • Zdeněk Loose
  • Josef Psutka
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6231)

Abstract

In the paper we introduce the on-line captioning system developed by our teams and used by the Czech Television (CTV), the public service broadcaster in the Czech Republic.

The research project is targeted at incorporation of speech technologies into the CTV environment. One of the key missions is the development of captioning system supporting captioning of a “live” acoustic track. It can be either the real audio stream or the audio stream produced by a shadow speaker. Another key mission is to develop software tools and techniques usable for training the shadow speakers.

During the initial phases of the project we concluded that the broadcasting of the Parliamentary meetings of the Chamber of Deputies fulfills the necessary conditions that enable it to be captioned without the aid of the shadow speaker. We developed a fully automatic captioning pilot system making the broadcasting of Parliamentary meetings of the Chamber of Deputies accessible to the hearing impaired viewers.

The pilot run enabled us and our partners in the Czech TV to develop and evaluate the complete captioning infrastructure and collect, review and possibly implement opinions and suggestions of the targeted audience.

This paper presents our experience gathered during first years of the project to the public audience.

Keywords

Speech Recognition Acoustic Model Audio Stream Public Service Broadcaster Acoustic Track 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Evans, M.J.: Speech Recognition in Assisted and Live Subtitling for Television. White Paper WHP065, BBC Research & Development (2003)Google Scholar
  2. 2.
    Homma, S., Kobayashi, A., Oku, T., Sato, S., Imai, T., Takagi, T.: New Real-Time Closed-Captioning System for Japanese Broadcast News Programs. In: Miesenberger, K., Klaus, J., Zagler, W.L., Karshmer, A.I. (eds.) ICCHP 2008. LNCS, vol. 5105, pp. 651–654. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  3. 3.
    Saraclar, M., Riley, M., Bocchieri, E., Goffin, V.: Towards Automatic Closed Captioning: Low Latency Real Time Broadcast News Transcription. In: Seventh International Conference on Spoken Language Processing (2002)Google Scholar
  4. 4.
    Boulianne, G., Beaumont, J., Boisvert, M., Brousseau, J., Cardinal, P., Chapdelaine, C., Comeau, M., Ouellet, P., Osterrath, F.: Computer-Assisted Closed-Captioning of Live TV Broadcasts in French. In: Ninth International Conference on Spoken Language Processing (2006)Google Scholar
  5. 5.
    Povey, D.: Discriminative Training for Large Vocabulary Speech Recognition. Ph.D. thesis, Cambridge University, Engineering Department (2003)Google Scholar
  6. 6.
    Pražák, A., Müller, L., Psutka, J. V., Psutka, J.: LIVE TV SUBTITLING – Fast 2-pass LVCSR System for Online Subtitling. In: SIGMAP 2007, International Conference on Signal Processing and Multimedia Applications (2007)Google Scholar
  7. 7.
    Pražák, A., Psutka, J., Hoidekr, J., Kanis, J., Müller, L., Psutka, J.: Automatic Online Subtitling of the Czech Parliament Meetings. In: newblock Lecture Notes in Artificial Intelligence. LNCS (LNAI), pp. 501–508. Springer, Heidelberg (2006)Google Scholar
  8. 8.
    EIA-608-B: Recommended Practice for Line 21 Data Service. Technical Report EIA/ANSI 608-B, Electronic Industries Alliance (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Jan Trmal
    • 1
  • Aleš Pražák
    • 2
  • Zdeněk Loose
    • 1
  • Josef Psutka
    • 1
  1. 1.Department of CyberneticsUniversity of West BohemiaPilsenCzech Republic
  2. 2.SpeechTech, s.r.oPlzenCzech Republic

Personalised recommendations