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) +2

Partially Adaptive Multichannel Joint Reduction of Ego-noise and Environmental Noise

no code implementations • 27 Mar 2023 • Huajian Fang, Niklas Wittmer, Johannes Twiefel, Stefan Wermter, Timo Gerkmann

In this paper, we propose a multichannel partially adaptive scheme to jointly model ego-noise and environmental noise utilizing the VAE-NMF framework, where we take advantage of spatially and spectrally structured characteristics of ego-noise by pre-training the ego-noise model, while retaining the ability to adapt to unknown environmental noise.

Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks

no code implementations • 7 Jun 2017 • Marian Tietz, Tayfun Alpay, Johannes Twiefel, Stefan Wermter

Ladder networks are a notable new concept in the field of semi-supervised learning by showing state-of-the-art results in image recognition tasks while being compatible with many existing neural architectures.