The goal of the ASR track is the transcription of audio coming from unsegmented TED and TEDx talks.
Languages: English, German, and Italian
Input format: unsegmented SPHERE, 16kHz, 16bit, PCM
Output format: CTM, no case, no punctuation, UTF-8. Confidence measures are optional, but appreciated
Development Data
English development data: dev2010, tst2010 and dev2012 Note: for the ASR track, only an uem file similar to dev2010.uem and dev2012.uem will be provided, i.e. without sentence segmentation! Therefore, automatic segmentation of the data is mandatory!
German development data: dev2012 Note: for the ASR track, only an uem file similar to dev2012.de-en.de.uem will be provided, i.e. without sentence segmentation! Therefore, automatic segmentation of the data is mandatory!
Italian development data: dev2014.
Evaluation Data
English tst2014 + tst2013 (progressive)
Italian tst2014
Submission Guidelines
ASR Run Submission Format:
Each participant has to submit at least one run for each of the tasks s/he registered for.
Multiple run submissions are allowed, but participants must explicitly indicate one PRIMARY run for each track. All other run submissions are treated as CONTRASTIVE runs. In case that none of the runs is marked as PRIMARY, the latest submission (according to the file time-stamp) for the respective track will be used as the PRIMARY run.
Runs have to be submitted as a gzipped TAR archive (format see below) and sent as an email attachment to sebastian.stueker@kit.edu and cettolo@fbk.eu
Submissions have to be made in CTM format. See the ctm documentation in the NIST SCTK documentation for details. The confidence values are optional. The channel number has to be '1'. Scoring will be case-insensitive. Submissions have to be in UTF-8.
Output conventions
The text will be scored case-insensitive, but can be submitted case-sensitive
Numbers, dates etc. need to be transcribed in words as they are spoken, not in digits
Common acronyms such as NATO, EU, are written as one word, without any special markers between the letters. This applies no matter whether they are spoken as one word or spelled out as a letter sequence
All other letter spelling sequences are written as individual letters with space inbetween
Standard abbreviations, such as "etc." "Mr." are accepted as specified by the glm file in the scoring package
For words pronounced in their contracted form, the orthography for the contracted form may be used. These cases will be normalized by the glmfile to their canonical form.
TAR archive file structure:
< UserID >/< Set >.< Task >.< UserID >.primary.ctm
/< Set >.< Task >.< UserID >.contrastive1.ctm
/< Set >.< Task >.< UserID >.contrastive2.ctm
/...
where:
< UserID > = user ID of participant used to download data files
< Set > = tst2014|tst2013
< Task > = ASR_ENG | ASR_GER | ASR_ITA
Examples:
fbk/tst2014.ASR_ENG.fbk.primary.ctm
/tst2014.ASR_ENG.fbk.contrastive1.ctm
Re-submitting your runs is allowed as far as the mails arrive BEFORE the submission deadline. In case that multiple TAR archives are submitted by the same participant, only runs of the most recent submission mail will be used for the IWSLT 2014 evaluation and previous mails will be ignored.