End-to-End Recognition of Spontaneous Speech on the Hungarian BEA Database
  • Metaadatok
Tartalom: https://ojs.mtak.hu/index.php/besztud/article/view/5673
Archívum: Beszédtudomány - Speech Science
Gyűjtemény: Tanulmányok
Cím:
End-to-End Recognition of Spontaneous Speech on the Hungarian BEA Database
Létrehozó:
Fekete, Tímea
Mihajlik, Péter
Kiadó:
Hungarian Research Institute for Linguistics
Dátum:
2022-01-29
Téma:
end-to-end speech recognition
deep neural networks
spontaneous speech
Hungarian
Tartalmi leírás:
The end-to-end deep neural network based speech recognition approach is increasingly popular due to its fully data driven nature - no language-specific knowledge is needed beyond the transcribed speech data. However, most of the end-to-end speech recognition experiments are performed on read (planned) speech and no Hungarian language results are available for the Speech Community. In this paper, we make the first attempt to train and evaluate a Hungarian speech recognition system based on the studio-quality Hungarian BEA (Spoken Language Speech Database) in an end-to-end neural manner. We present the challenge of recognising spontaneous speech: even without any significant background noise, the word error rate on spontaneous speech is an order of magnitude higher than in the case of planned speech - both recorded with the same speakers in the same environment. This emphasises the need for more thorough studies of spontaneous speech and possibly for more data.
Nyelv:
angol
Típus:
info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
A tanulmányokat szakterületi kompetenciával rendelkező szakemberek lektorálták.
Formátum:
application/pdf
Azonosító:
10.15775/Besztud.2021.261-272
Forrás:
Beszédtudomány - Speech Science; Évf. 2 szám 1 (2021): Beszédtudomány - Speech Science; 261-272
2732-3773
10.15775/Besztud.2021
Kapcsolat:
Létrehozó:
Copyright (c) 2021 Beszédtudomány - Speech Science