VIADAT-REPO is an additional module to the lindat-dspace platform which allows for depositing data records in the field of oral history, including its specific metadata workflow; it has been created within the VIADAT project and as such will be a part of a "virtual assistant" for processing, annotation, enrichment and accessing of audio and video recordings. This package contains VIADAT-DEPOSIT module; bundled with VIADAT-REPO to ease the integration.
VIADAT-SEARCH in connection with VIADAT-REPO enables searching transcripts of oral history recordings. Language analysis has been used to preprocess the recordings, which makes it possible to search the fulltext using multiple criteria, including names, different forms of the same word etc.
Developed in cooperation with ÚSD AV ČR and NFA.
A VIADAT module; the purpose of VIADAT-STAT is statistical analysis of recordings stored by the platform.
Developed in cooperation with ÚSD AV ČR and NFA.
A VIADAT module; the purpose of VIADAT-STAT is statistical analysis of recordings stored by the platform.
Developed in cooperation with ÚSD AV ČR and NFA.
Victor is a web page cleaning tool. It is aimed at removing menu, ads, footers, headers, etc. from HTML web pages, so that only main web page content remains. Victor is based on a conditional random fields algorithm.
Victoria is an on-line HTML web page annotation tool suitable for selecting texts on the web pages. It can be used to mark important/interesting parts of web pages for further processing.
This program enables the user to visualize f0 contours, to plot vowels in the F1/F2 space for multiple points in the vowel interval, e.g. at 20%, 50% and 80%, and to visualize vowel durations.
(The tool is implemented in R. We used the following packages: phonR, gplots, plotrix, lattice, readxl, WriteXLS, DT,
psych and pracma. We thank the developers of these packages.)
Vystadial 2013 is a dataset of telephone conversations in English and Czech, developed for training acoustic models for automatic speech recognition in spoken dialogue systems. It ships in three parts: Czech data, English data, and scripts.
The data comprise over 41 hours of speech in English and over 15 hours in Czech, plus orthographic transcriptions. The scripts implement data pre-processing and building acoustic models using the HTK and Kaldi toolkits.
This is the scripts part of the dataset. and This research was funded by the Ministry of
Education, Youth and Sports of the Czech Republic under the grant agreement
LK11221.