A Dutch-only wav2vec 2.0 large model, pre-trained on 55.7k hours of WhisperX-cleaned TV audio, outperformed reported multi-lingual and Whisper baselines on the Dutch N-Best benchmark.
We note that most self-supervised learning methods are solely developed on LS-like data, simply due to ease of ac- cess and availability of read speech
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Self-supervised learning of speech representations with Dutch archival data
A Dutch-only wav2vec 2.0 large model, pre-trained on 55.7k hours of WhisperX-cleaned TV audio, outperformed reported multi-lingual and Whisper baselines on the Dutch N-Best benchmark.