No abstract

This paper reports on an experiment aimed at establishing how phonetic transcriptions for the large CGN corpus can be obtained most efficiently. This experiment explores the po tential of an automatically generated transcription (AGT) by comparing an AGT with a reference transcription (Tref) of the same material, to determine whether and how the AGT can be improved to make it more similar to Tref. The results indicate that the AGT can be optimized through pronunciation variation modelling so as to make human corrections more efficient or even superfluous, at least for some speech styles.

No abstract

An open source database of hand-segmented Dutch speech was constructed with off-the-shelf software using speech from 8 speakers in a variety of speaking styles. For a total of 50,000 words, speech acquisition and preparation took around 3 person-weeks per speaker. Hand segmentation took 1,000 hours of labeling altogether. The asymptotic segmentation speed was about one word, or four boundaries, per minute. An evaluation showed that the Median Absolute Difference of the segment boundaries was 6 ms between labelers, and 4 ms within labelers. Label differences (substitutions, insertions, and deletions) were found in 8% of the segments between labelers and 5% within labelers. Compiled data are available in relational database format for querying with SQL.

In this paper we report on a project about Dutch Human Language Technologies (HLT) resources. In this project we first defined a so-called BLARK (Basic LAnguage Resources Kit). Subsequently, a survey was carried out to make an inventory and evaluation of existing Dutch HLT resources. Based on the information collected in the survey, a priority list was drawn up of materials that need to be developed to complete the Dutch BLARK. Although the current project only concerns the Dutch language, the method employed and some of the results are also relevant for other languages.