DementiaBank German PARLO Corpus



Franziska Braun
--
Technische Hochschule, Nürnberg

Korbinian Riedhammer
--
Technische Hochschule, Nürnberg
Participants: 208
Type of Study: naturalistic
Location: Germany
Media type: audio

Browsable transcripts

Download transcripts

Media folder

Citation information

Braun, F., Witzl, C., Hönig, F., Nöth, E., Bocklet, T., & Riedhammer, K. (2026). The PARLO Dementia Corpus: A German Multi-Center Resource for Alzheimer's Disease. In Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026), pages 9581–9591, Palma, Mallorca, Spain. European Language Resources Association (ELRA). pdf here

Project Description

The **PARLO Dementia Corpus (PDC)** is a German multi-center clinical speech corpus collected at nine academic memory clinics. This release provides the recordings as audio (`wav/`), manual professional transcripts (`transcripts/`), and CLAN/CHAT files with word-level time alignments (`CHAT/`). The raw forced-alignment word tables are also included under `alignments/`. Recording used an iPad-based protocol with eight speech tasks. Participants included 83 healthy controls, 59 MCI, and 66 AD. File names have participant ID and task name.

Further information is in this readme file

Metadata described in the readme.txt are in this file.

Tasks included

The word-repetition recordings have professional transcripts, but no alignments or chat files.