The Journal of the Acoustical Society of Korea

The Acoustical Society of Korea (한국음향학회)
권호 표지

A Study on the Language Independent Dictionary Creation Using International Phoneticizing Engine Technology

국제 음소 기술에 의한 언어에 독립적인 발음사전 생성에 관한 연구

  • Published : 2007.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

One result of the trend towards globalization is an increased number of projects that focus on natural language processing. Automatic speech recognition (ASR) technologies, for example, hold great promise in facilitating global communications and collaborations. Unfortunately, to date, most research projects focus on single widely spoken languages. Therefore, the cost to adapt a particular ASR tool for use with other languages is often prohibitive. This work takes a more general approach. We propose an International Phoneticizing Engine (IPE) that interprets input files supplied in our Phonetic Language Identity (PLI) format to build a dictionary. IPE is language independent and rule based. It operates by decomposing the dictionary creation process into a set of well-defined steps. These steps reduce rule conflicts, allow for rule creation by people without linguistics training, and optimize run-time efficiency. Dictionaries created by the IPE can be used with the Sphinx speech recognition system. IPE defines an easy-to-use systematic approach that can lead to internationalization of automatic speech recognition systems.

Keywords

References

  1. H.J.M, Steeneken, and L.F. Lamel, 'SQ UALE : Speech Recognizer Quality Assessment for Linguistic Engineering', Proceedings ARPA Workshop on Spoken Language Technology, Plainsboro, New Jersey, 1994
  2. J .-L. Gauvain and L. Lamel, 'Large vocabulary continuous speech recognition: Advances and application,' Proc. IEEE, 88 (8) 1181-1200, 2000
  3. H.J.M. Steeneken, and L,F. Lamel, 'SQUALE : Speech Recognizer Quality Assessment for Linguistic Engineering', Proceedings ARPA Workshop on Spoken Language Technology, Plainsboro, New Jersey, 1994
  4. T. Matsuoka, K. Ohtsuki, T. Mori, S. Furui and K. Shirai, 'Large¬Vocabulary Continuous-Speech Recognition Using a Japanese Business Newspaper (NIKKEI),' Proc. Of the ARPA Workshop on Spoken Language Technology, Austin TX, Morgan Kaufmann, Cohen, Ed., 1996
  5. R.I. Damper 'Self-learning and connectionist approaches to text-to-phoneme conversion', in Connectionst Models of Memory and Language, Levy J., Bairaktaris J., Bullinaria J .. and Cairns p. (eds,), UCL Press, London, 117-144, 1995
  6. L. Deng, 'Integrated-multilingual Speech Recognition using Universal Features in a functional Speech Production Model,' ICASSP '97, 1007-1010, 1997
  7. R., Federking, A .. Rudnicky, C., Hogan, Eskenazi, 'M. DIPLOMAT,' ACL-EACL '97, 1997
  8. T,J. Sejnowski, and C.R., Rosenberg, 'Nettalk: a parallel network that learns to read aloud,' The Johns Hopkins University Electrical Engineering and Computer Science Technical Report, JHU/EECS-86/01, 1986
  9. M. J. Bert V. Coile, 'The DEPES Development System for Text-to-Speech Synthesis,' ICASSP '89, 250-253, 1989
  10. S. Hertz, 'From text-to-speech with SRS,' Journal of the Acoustical Society of America, 1155-1171, 1982
  11. The Unicode Consortium, The Unicode Standard, version 2.0, (Addison¬Wesley Publishing Company, 1996