NEWS
Last update: 1 December 2023
16 November 2023: Music Emotions in Solo Piano: Bridging the Gap Between Human Perception and Machine Learning presented at CMMR 2023, Tokyo, Japan
- Our Poster was presented at the 16th International Symposium on Computer Music Multidisciplinary Research in Tokyo
20 May 2022: PhdThesis Published
-
My PhD Thesis entitled "Bag-of-Words Representations for Computer Audition" has been published by OPUS, University of Augsburg:
https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-942798
14 March 2022: "Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap"
- A pre-print of our work on transformer models (mainly wav2vec 2.0) was published on arxiv.org:
https://arxiv.org/abs/2203.07378
We investigate the aspects of robustness and fairness in foundation models for Speech Emotion Recognition and show that implicit linguistic information can be learnt by these models, resulting in an improved performance for Valence recognition, compared to previous deep learning-based models.