The TalkBank Project at Carnegie Mellon University has been established
as a CLARIN-K Knowledge Centre for Language Learning Analysis (CLARIN-Learn).
We seek to provide resources, methods, and advice to assist researchers
interested in using corpora to study language learning, recovery, and
processing. We hope that, through this process, researchers will create
new corpora and new ways of analyzing language. Our centre is happy to
provide these services:
We can provide advice on the use of the existing data sets in the
various component corpora in TalkBank, including CHILDES, CABank,
SLABank, SamtaleBank, AphasiaBank, BilingBank, HomeBank, PhonBank,
FluencyBank, and others.
Because many of these corpora include transcripts linked to audio or
video, we can also provide help on methods for multimedia and gesture
We can provide pointers to relevant corpora outside of TalkBank,
particularly including those at other CLARIN centres.
We can provide methods for allowing researchers to contribute new data
to any of the TalkBank archives.
We can provide help in the use of analytic tools with a focus on use of
the CLAN, Phon, Praat, ANNIS, and Elan programs. These tools all operate
well on data from TalkBank.
We can provide some limited help in the use of R and R scripts for
In collaboration with Yvan Rose at Memorial University, we can provide
help regarding details of phonological analysis with PHON and its
integration with Praat.
We can provide this help through email or Skype. Questions will be
accepted in English, German, Spanish, Hungarian, or French will be
accepted, with responses provided in English. We also maintain Google
Groups lists for CHILDES, PhonBank, AphasiaBank, and the CLAN program
that can help in the support and learning process.