Automatic transcription of Czech language oral history in the MALACH project: Resources and initial experiments
In this paper we describe the initial stages of the ASR component of the MALACH
(Multilingual Access to Large Spoken Archives) project. This project will attempt to provide …
(Multilingual Access to Large Spoken Archives) project. This project will attempt to provide …
Recording and annotation of speech corpus for Czech unit selection speech synthesis
J Matoušek, J Romportl - International Conference on Text, Speech and …, 2007 - Springer
The paper gives a brief summarisation of preparation and recording of a phonetically and
prosodically rich speech corpus for Czech unit selection text-to-speech synthesis. Special …
prosodically rich speech corpus for Czech unit selection text-to-speech synthesis. Special …
Formal prosodic structures and their application in NLP
J Romportl, J Matoušek - International Conference on Text, Speech and …, 2005 - Springer
A formal prosody description framework is introduced together with its relation to language
semantics and NLP. The framework incorporates deep prosodic structures based on a …
semantics and NLP. The framework incorporates deep prosodic structures based on a …
The Nijmegen corpus of casual Czech
M Ernestus, L Kočková-Amortová… - LREC 2014: 9th …, 2014 - pure.mpg.de
This article introduces a new speech corpus, the Nijmegen Corpus of Casual Czech
(NCCCz), which contains more than 30 hours of high-quality recordings of casual …
(NCCCz), which contains more than 30 hours of high-quality recordings of casual …
General framework for mining, processing and storing large amounts of electronic texts for language modeling purposes
The paper describes a general framework for mining large amounts of text data from a
defined set of Web pages. The acquired data are meant to constitute a corpus for training …
defined set of Web pages. The acquired data are meant to constitute a corpus for training …
[PDF][PDF] Automatic segmentation of speech into sentence-like units
J Kolář - 2008 - kky-sw.zcu.cz
AUTOMATIC SEGMENTATION OF SPEECH INTO SENTENCE-LIKE UNITS Ing. Jáchym Kolář
Page 1 University of West Bohemia in Pilsen Faculty of Applied Sciences AUTOMATIC …
Page 1 University of West Bohemia in Pilsen Faculty of Applied Sciences AUTOMATIC …
Czech spontaneous speech collection and annotation: The database of technical lectures
J Rajnoha, P Pollák - Cross-Modal Analysis of Speech, Gestures, Gaze …, 2009 - Springer
Applying speech recognition into real working systems, spontaneous speech recognition
has increasing importance. For the development purposes of such applications, the need of …
has increasing importance. For the development purposes of such applications, the need of …
Design, creation, and analysis of Czech corpora for structural metadata extraction from speech
J Kolář - Language resources and evaluation, 2011 - Springer
Structural metadata extraction (MDE) research aims to develop techniques for automatic
conversion of raw speech recognition output to forms that are more useful to humans and …
conversion of raw speech recognition output to forms that are more useful to humans and …
[PDF][PDF] Fitting class-based language models into weighted finite-state transducer framework.
In our paper we propose a general way of incorporating classbased language models with
many-to-many word-to-class mapping into the finite-state transducer (FST) framework. Since …
many-to-many word-to-class mapping into the finite-state transducer (FST) framework. Since …