Search Results

You are looking at 1 - 2 of 2 items for

  • Author or Editor: Tibor Révész x
  • User-accessible content x
Clear All Modify Search

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.

Full access
Orvosi Hetilap
Authors: , Budapest, Üllői út 78., 1082, Csilla András, Péter Bartek, István Battyáni, János Bezsilla, György Bodoky, Barna Bogner, Attila Bursics, Tibor Csőszi, László Damjanovich, Magdolna Dank, Zsófia Dankovics, Pál Ákos Deák, Kristóf Dede, Attila Doros, Ibolyka Dudás, Tamás Györke, Oszkár Hahn, Erika Hartmann, Erika Hitre, Zsolt Horváth, Marianna Imre, Károly Kalmár Nagy, Zsolt Káposztás, László Kóbori, Péter Kupcsulik, László Landherr, Zoltán Lóderer, László Mangel, Zoltán Máthé, Tamás Mersich, Klára Mezei, Elemér Mohos, Attila Oláh, Péter Pajor, András Palkó, Zsuzsanna Pápai, András Papp, Mihály Patyánik, András Petri, János Révész, Ágnes Ruzsa, Krisztina Schlachter, László Sikorszki, István Sipőcz, Eszter Székely, Attila Szijártó, László Torday, Lajos Barna Tóth, Edit Dósa, László Harsányi, Gábor István, László Landherr, György Lázár, József Lövey, Zsuzsa Schaff, Ákos Szűcs, and András Vereczkei
Open access