Accessing

Accessing

Analysing

Analysing

Preparation and Depositing

Preparation

 

More

More

Help

Help

More

Automatic phonetic labelling & segmentation of multiple Hungarian recordings

Interviews and conversation are often recorded and later transcribed. The web service WebMAUS Basic available in the CLARIN infrastructure provides tools to combine audio recordings and transcriptions in a way that the phonemes, words and sentences are time aligned with the corresponding audio signals. Using praat, it is then possible to directly go to a relevant part. The service provides the opportunity to edit whole corpora in batch mode.  

Especially relevant for

  • Linguists
  • Phoneticians
  • Speech technologists
  • Anthropologists
  • Ethnologists
  • Media scientists 

Starting point:

50 recordings of Hungarian (*.wav) and 50 orthographic transcripts (*.txt)

Goal:

50 hierarchical segmentations (words, phonology, phones) in praat compatible format (*.TextGrid); phonetic segments should be encoded in IPA

Solution:

Web Interface BAS WebMAUS Basic

Related CLARIN-D tools and services

 

Short guide on how to use BAS WebMAUS Multiple

Preparation:

  1. download the ZIP package ftp://clarin.phonetik.uni-muenchen.de/BASWebServices/useCases/multipleFileSegmentation.zip and
  2. un-pack it onto your local desktop folder; there should be a directory called 'multipleFileSegmentation' on your desktop.

By Web Interface:

  1. go to http://clarin.phonetik.uni-muenchen.de/BASWebServices
  2. select service 'WebMAUS Basic'
  3. open the directory 'multipleFileSegmentation/Corpus' on your desktop; select all 50 *.wav and 50 *.txt files; drag&drop them to the designated drop area of the service. The drop might take a few seconds, so please be patient. All 100 files should be visible in the drop area after completion.
  4. press button 'Upload' after the upload is completed you can inspect the uploaded text files or listen to the uploaded signals by clicking on the file link in the drop area.
  5. execute WebMAUS with the following options (no need to adjust the other options)
    • Language = Hungarian
    • KAN tier in TextGrid = true
    • ORT tier in TextGrid = true
    • Chunk segmentation = force
    • Output symbols = ipa
  6. Confirm the terms-of-usage and press the button 'Run Web Service'
  7. after completion the resulting 50 *.TextGrid files are shown below; click on "Download as ZIP-File" to download all files to your local system
  8. start praat (download at praat.org) on your local system and open *.TextGrid *.wav pairs to inspect the segmentation