| SERAB: A multi-lingual benchmark for speech emotion recognition N Scheidwasser-Clow, M Kegler, P Beckmann, M Cernak ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2021 | 44 | 2021 |
| Deep speech inpainting of time-frequency masks M Kegler, P Beckmann, M Cernak Proc. Interspeech 2020, 3276-3280, 2020 | 42 | 2020 |
| Word-level embeddings for cross-task transfer learning in speech processing P Beckmann, M Kegler, M Cernak 2021 29th European Signal Processing Conference (EUSIPCO), 446-450, 2021 | 34* | 2021 |
| Byol-s: Learning self-supervised speech representations by bootstrapping G Elbanna, N Scheidwasser-Clow, M Kegler, P Beckmann, K El Hajal, ... HEAR: Holistic Evaluation of Audio Representations, 25-47, 2022 | 15 | 2022 |
| Hybrid Handcrafted and Learnable Audio Representation for Analysis of Speech Under Cognitive and Physical Load G Elbanna, A Biryukov, N Scheidwasser-Clow, L Orlandic, P Mainar, ... Proc. Interspeech 2022, 386-390, 2022 | 9 | 2022 |
| An alternative to cognitivism: computational phenomenology for deep learning P Beckmann, G Köstner, I Hipólito Minds and Machines 33 (3), 397-427, 2023 | 6* | 2023 |
