348 citations · 384 across the 8 of their papers we have counts for
8 papers
Wav2Small: Distilling Wav2Vec2 to 72K parameters for Low-Resource Speech emotion recognition
Dionyssos Kounadis-Bastian, Oliver Schrüfer, Anna Derington +4
Speech Emotion Recognition (SER) needs high computational resources to overcome the challenge of substantial annotator disagreement. Today SER is shifting towards dimensional annot…
Testing Correctness, Fairness, and Robustness of Speech Emotion Recognition Models
Anna Derington, Hagen Wierstorf, Ali Özkil +3
Machine learning models for speech emotion recognition (SER) can be trained for different tasks and are usually evaluated based on a few available datasets per task. Tasks could in…
Speech-based Age and Gender Prediction with Transformers
Felix Burkhardt, Johannes Wagner, Hagen Wierstorf +2
We report on the curation of several publicly available datasets for age and gender prediction. Furthermore, we present experiments to predict age and gender with models based on a…
audb -- Sharing and Versioning of Audio and Annotation Data in Python
Hagen Wierstorf, Johannes Wagner, Florian Eyben +2
Driven by the need for larger and more diverse datasets to pre-train and fine-tune increasingly complex machine learning models, the number of datasets is rapidly growing. audb is…
Probing Speech Emotion Recognition Transformers for Linguistic Knowledge
Andreas Triantafyllopoulos, Johannes Wagner, Hagen Wierstorf +5
Large, pre-trained neural networks consisting of self-attention layers (transformers) have recently achieved state-of-the-art results on several speech emotion recognition (SER) da…
Dawn of the transformer era in speech emotion recognition: closing the valence gap
Johannes Wagner, Andreas Triantafyllopoulos, Hagen Wierstorf +4
Recent advances in transformer-based architectures which are pre-trained in self-supervised manner have shown great promise in several machine learning tasks. In the audio domain,…
Referenceless Performance Evaluation of Audio Source Separation using Deep Neural Networks
Emad M. Grais, Hagen Wierstorf, Dominic Ward +2
Current performance evaluation for audio source separation depends on comparing the processed or separated signals with reference signals. Therefore, common performance evaluation…
Multi-Resolution Fully Convolutional Neural Networks for Monaural Audio Source Separation
Emad M. Grais, Hagen Wierstorf, Dominic Ward +1
In deep neural networks with convolutional layers, each layer typically has fixed-size/single-resolution receptive field (RF). Convolutional layers with a large RF capture global i…