Gaps to Bridge in Speech Technology

  • Géza Németh
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8773)

Abstract

Although recently there has been significant progress in the general usage and acceptance of speech technology in several developed countries there are still major gaps that prevent the majority of possible users from daily use of speech technology-based solutions. In this paper some of them are listed and some directions for bridging these gaps are proposed. Perhaps the most important gap is the "Black box" thinking of software developers. They suppose that inputting text into a text-to-speech (TTS) system will result in voice output that is relevant to the given context of the application. In case of automatic speech recognition (ASR) they wait for accurate text transcription (even punctuation). It is ignored that even humans are strongly influenced by a priori knowledge of the context, the communication partners, etc. For example by serially combining ASR + machine translation + TTS in a speech-to-speech translation system a male speaker at a slow speaking rate might be represented by a fast female voice at the other end. The science of semantic modelling is still in its infancy. In order to produce successful applications researchers of speech technology should find ways to build-in the a priori knowledge into the application environment, adapt their technologies and interfaces to the given scenario. This leads us to the gap between generic and domain specific solutions. For example intelligibility and speaking rate variability are the most important TTS evaluation factors for visually impaired users while human-like announcements at a standard rate and speaking style are required for railway station information systems. An increasing gap is being built between "large" languages/markets and "small" ones. Another gap is the one between closed and open application environments. For example there is hardly any mobile operating system that allows TTS output re-direction into a live telephone conversation. That is a basic need for rehabilitation applications of speech impaired people. Creating an open platform where "smaller" and "bigger" players of the field could equally plug-in their engines/solutions at proper quality assurance and with a fair share of income could help the situation. In the paper some examples are given about how our teams at BME TMIT try to bridge the gaps listed.

Keywords

Gaps in speech technology domain-specific applications open platform user preferences 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Voice Synthesis Nearing Growth Explosion, Computerworld (August 31, 1981) Google Scholar
  2. 2.
    Brown, M.: The “Lost” Steve Jobs Speech from 1983; Foreshadowing Wireless Networking, the iPad, and the App Store. In: Talk by Steve Jobs at International Design Conference in 1983, October 2 (2012) (retrieved July 2014)Google Scholar
  3. 3.
    The Global Language Technology Market, LT-Innovate, p. 11 (October 2012)Google Scholar
  4. 4.
    Handley, Z.: Is text-to-speech synthesis ready for use in computer-assisted language learning? Speech Communication 51(10), 906–919 (2009)CrossRefGoogle Scholar
  5. 5.
    Németh, G., Zainkó, C., Fekete, L., Olaszy, G., Endrédi, G., Olaszi, P., Kiss, G., Kiss, P.: The design, implementation and operation of a Hungarian e-mail reader. International Journal of Speech Technology 3/4, 216–228 (2000)Google Scholar
  6. 6.
    Németh, G., Zainkó, C., Kiss, G., Olaszy, G., Fekete, L., Tóth, D.: Replacing a Human Agent by an Automatic Reverse Directory Service. In: Magyar, G., Knapp, G., Wojtkowski, W., Wojtkowski, G., Zupancic, J. (szerk.) Advances in Information Systems Development: New Methods and Practice for the Networked Society, pp. 321–328. Springer (2007)Google Scholar
  7. 7.
    Németh, G., Fék, M., Csapó, T.G.: Increasing Prosodic Variability of Text-To-Speech Synthesizers. In: Interspeech 2007, Antwerpen, Belgium, pp. 474–477 (2007)Google Scholar
  8. 8.
    Csapó, T.G., Németh, G.: Modeling irregular voice in statistical parametric speech synthesis with residual codebook based excitation. IEEE Journal on Selected Topics In Signal Processing 8(2), 209–220 (2014)CrossRefGoogle Scholar
  9. 9.
    Olaszy, G., Németh, G., Olaszi, P., Kiss, G., Gordos, G.: PROFIVOX - A Hungarian Professional TTS System for Telecommunications Applications. International Journal of Speech Technology 3(3/4), 201–216 (2000)CrossRefMATHGoogle Scholar
  10. 10.
    Csala, E., Németh, G., Zainkó, C.: Application of the NAO humanoid robot in the treatment of marrow-transplanted children. In: Péter, B. (ed.) 2012 IEEE 3rd International Conference on Cognitive Infocommunications (CogInfoCom), Kosice, Slovakia, pp. 655–658 (2012)Google Scholar
  11. 11.
    Németh, G., Zainkó, Cs., Bartalis, M., Olaszy, G., Kiss, G.: Human Voice or Prompt Generation? Can They Co-Exist in an Application? In: Interspeech 2009: Speech and Intelligence, Brighton, UK, pp. 620–623 (2009) Google Scholar
  12. 12.
    Klabbers, E.A.M.: High-Quality Speech Output Generation through Advanced Phrase Concatenation. In: COST Telecom Workshop, Rhodes, Greece, pp. 85–88 (September 1997)Google Scholar
  13. 13.
    Nagy, A., Pesti, P., Németh, G., Bőhm, T.: Design issues of a corpus-based speech synthesizer. HÍRADÁSTECHNIKA LX:(6), 6–12 (2005)Google Scholar
  14. 14.
    Németh, G., Kiss, G., Tóth, B.: Cross Platform Solution of Communication and Voice/Graphical User Interface for Mobile Devices in Vehicles. In: Abut, H., Hansen, J.H.L., Takeda, K. (eds.) Advances for In-Vehicle and Mobile Systems: Challenges for International Standards, pp. 237–250. Springer (2005)Google Scholar
  15. 15.
    Tóth, B., Németh, G.: Hidden Markov Model Based Speech Synthesis System in Hungarian. Infocommunications Journal LXIII:(7), 30–34 (2008)Google Scholar
  16. 16.
    Zainkó, C., Tóth, B.P., Bartalis, M., Németh, G., Fegyó, T.: Some Aspects of Synthetic Elderly Voices in Ambient Assisted Living Systems. In: Burileanu, C., Teodorescu, H.-N., Rusu, C. (eds.) Proceedings of the 7th International Conference Speech Technology and Human-Computer Dialogu, Cluj-Napoca, Romania, pp. 185–189. IEEE, New York (2013)Google Scholar
  17. 17.
    Németh, G., Olaszy, G., Csapó, T.G.: Spemoticons: Text-To-Speech based emotional auditory cues”m. In: ICAD 2011, Budapest, Magyarország, pp. 1–7. Paper Keynote 3 (2011)Google Scholar
  18. 18.
    Ethnologue, SIL International (retrieved July 2014)Google Scholar
  19. 19.
    META-NET White Paper series on Europe’s Languages in the Digital Age (2013), http://www.meta-net.eu/whitepapers/key-results-and-cross-language-comparison (retrieved July 2014)
  20. 20.
    Németh, G., Zainkó, C.: Multilingual Statistical Text Analysis, Zipf’s Law and Hungarian Speech Generation. Acta Linguistica Hungarica 49:(3-4), 385–405 (2002)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Géza Németh
    • 1
  1. 1.Department of Telecommunications and Media Informatics (TMIT)Budapest University of Technology and Economics (BME)Hungary

Personalised recommendations