Skip to content

Detail of publication

Citation

Psutka, J. and Psutka Josef V.. and Ircing, P. : Czech Spontaneaous Speech – Acoustic&Language Models (MALACH) . Katedra kybernetiky, Fakulta aplikovaných věd, Západočeská univerzita v Plzni, Johns Hopkins University Baltimore, Shoah Visual History Foundation, 2005.

Abstract

The Visual History Foundation collected recently about 52 thousand testimonies of Holocaust survivors pronounced in 32 languages. There are approx. 570 Czech testimonies with a total length of 1 200 hours. It is not feasible to transcribe all those testimonies maually due to the enornous time and money demands. Thus the transcription is performed using the automatic speech recognition system – data forthe system development were acquired from the Czech Malach Speech Corpus. The basic AM unit is a triphone represented by a 5-state HMM, where every state is modeled as a GMM with 16 mixtures. The total number of states was reduced to 6699 using a phonetic clustering tree. The language model is designed as a combination of 2 bigram models.

Detail of publication

Title: Czech Spontaneaous Speech – Acoustic&Language Models (MALACH)
Author: Psutka, J. ; Psutka Josef V.. ; Ircing, P.
Language: English
Date of publication: 1 Jan 2005
Year: 2005
Type of publication: Prototype, software
Publisher: Katedra kybernetiky, Fakulta aplikovaných věd, Západočeská univerzita v Plzni, Johns Hopkins University Baltimore, Shoah Visual History Foundation
/ 2011-06-09 12:42:50 /

Keywords

Czech acoustic model, Czech language model, Speech recognition

BibTeX

@MISC{PsutkaJ_2005_CzechSpontaneaous,
 author = {Psutka, J. and Psutka Josef V.. and Ircing, P.},
 title = {Czech Spontaneaous Speech - Acoustic&Language Models (MALACH)},
 year = {2005},
 publisher = {Katedra kybernetiky, Fakulta aplikovan\'{y}ch v\v{e}d, Z\'{a}pado\v{c}esk\'{a} univerzita v Plzni, Johns Hopkins University Baltimore, Shoah Visual History Foundation},
 url = {http://www.kky.zcu.cz/en/publications/PsutkaJ_2005_CzechSpontaneaous},
}