View More View Less
  • 1 Department of Telecommunications and Telematics, Budapest University of Technology and Economics 1117 Bp. Magyar tudósok körútja 2.
  • | 2 Department of Telecommunications and Telematics, Budapest University of Technology and Economics 1117 Bp. Magyar tudósok körútja 2
  • | 3 Department of Telecommunications and Telematics, Budapest University of Technology and Economics 1117 Bp. Magyar tudósok körútja 2
Full access

Cross Mark

This paper discusses automatic phonetic transcription to be applied in Hungarian speech recognition. It first deals with the basic technologies of automatic speech recognition (ASR) for the sake of readers not familiar with this scientific field, then it discusses the place of (automatic) phonetic transcription in ASR. After that, our method developed for transcribing Hungarian texts automatically is introduced. This technique is an extension of the traditional linear transcription approach; its output is called 'optioned' because it contains pronunciation options in parallel arcs. We present our experiences with promising improvements in recogniser training efficiency. The achievements are due to the application of deeper linguistic (phonological) knowledge. With the training technique developed not only the quality of the acoustic models can be enhanced, but also, at the same time, the amount of the required manual work can effectively be decreased.

  • Rabiner, Lawrence - Biing-Hwang Juang 1993. Fundamentals of speech recognition. Prentice Hall, New Jersey.

    Fundamentals of speech recognition , ().

  • Fekete, László 1992. Magyar kiejtési szótár [Hungarian pronunciation dictionary]. Gondolat, Budapest.

    Magyar kiejtési szótár [Hungarian pronunciation dictionary] , ().

  • Hedvig, Olga - János Puster (eds) 1994. A magyar helyesírás szabályai [The spelling rules of Hungarian]. Akadémiai Kiadó, Budapest.

    A magyar helyesírás szabályai [The spelling rules of Hungarian] , ().

  • Szarvas, Máté - Tibor Fegyó - Péter Mihajlik - Péter Tatai 2000. Automatic recognition of Hungarian: Theory and practice. In: International Journal of Speech Technology 3: 237-51.

    'Automatic recognition of Hungarian: Theory and practice ' () 3 International Journal of Speech Technology : 237 -51.

    • Search Google Scholar
  • Szarvas, Máté - Sadaoki Furui (to appear). Finite-state transducer based Hungarian LVCSR with explicit modeling of phonological changes. Proceedings of ICSLP 2002.

    'Finite-state transducer based Hungarian LVCSR with explicit modeling of phonological changes.' , , .

    • Search Google Scholar
  • Vicsi, Klára 2002. MTBA - magyar nyelvű, telefon beszéd adatbázis [Hungarian telephony speech database].

  • (HTTP://WWW.TTT.BME.HU/SPEECH/MTBA.HTM)

  • Vicsi, Klára - Attila Vig 1998. Az első magyar nyelvű beszédadatbázis [The first Hungarian speech database]. In: Mária Gósy (ed.) Beszédkutatás '98 [Speech research '98], 163-77. MTA Nyelvtudományi Intézet, Budapest.

    Az első magyar nyelvű beszédadatbázis [The first Hungarian speech database] , ().

    • Search Google Scholar
  • Wothke, Klaus 1991. Automatic phonetic transcription taking into account the morphological structure of words. IBM Scientific Center Technical Report. Heidelberg.

    'Automatic phonetic transcription taking into account the morphological structure of words. ' () IBM Scientific Center Technical Report .

    • Search Google Scholar
  • Young, Steve - Dan Kershaw - Julian Odell - Dave Ollason - Valtcho Valtchev - Phil Woodland 2000. The HTK book. Microsoft, Cambridge.

    The HTK book , ().