Update Swiss German Speech Data Meeting Notes authored by Michael Graber's avatar Michael Graber
......@@ -20,11 +20,10 @@ Yixuan Xu, Daniel Perruchoud, Michael Graber
* possible solutions
* transcripts of Gemeinderat Zürich? -\> not available
* Synthetic Swiss German data?
* Daniel: Idiotikon data might be an option
* Daniel: Idiotikon data might be an option
* Permissive licence
* Ideally for stage 2 would be daily conversations, no bias towards political parliament data
* SRF -\> Ablation study could be done (\~ 2000 h)
* FHNW: Transcription Evaluation for SRF broadcast transcripts
* FHNW models perform substantially better than current SRF solution
* ![TranscriptionRatingDistributionSRFvsFHNW.png](uploads/f4f0cc084aa9daae243cf90cb83e3485/TranscriptionRatingDistributionSRFvsFHNW.png){width="504" height="360"}
......
......