Bring the Noise: Introducing Noise Robustness to Pretrained Automatic Speech Recognition

no code implementations • 5 Sep 2023 • Patrick Eickhoff, Matthias Möller, Theresa Pekarek Rosin, Johannes Twiefel, Stefan Wermter

We show that the Cleancoder is able to filter noise from speech and that it improves the total Word Error Rate (WER) of the downstream model in noisy conditions for both applications.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Replay to Remember: Continual Layer-Specific Fine-tuning for German Speech Recognition

no code implementations • 14 Jul 2023 • Theresa Pekarek Rosin, Stefan Wermter

While Automatic Speech Recognition (ASR) models have shown significant advances with the introduction of unsupervised or self-supervised training techniques, these improvements are still only limited to a subsection of languages and speakers.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3