Publications of project EVOLANG
2025
| Adaptation of Speech and Bioacoustics Models, , and , Idiap-RR-05-2025 |
|
| Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing, and , in: International Conference on Acoustics, Speech and Signal Processing, 2025 |
|
| CoRet: Improved Retriever for Code Editing, , in: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2025 |
[DOI] [URL] |
| Exploring auditory feedback mechanisms in speech recognition, and , in: Proceedings of Interspeech 2025, pages 4743-4747, 2025 |
[DOI] |
| Fine-Tuning Pretrained Models with NVIB for Improved Generalisation, , , , , , , , , , and , in: Workshop on Spurious Correlation and Shortcut Learning: Foundations and Solutions, 2025 |
[URL] |
| Leveraging Sequential Structure in Animal Vocalizations, and , Idiap-RR-06-2025 |
|
| Nonparametric Variational Information Bottleneck: Attention-based Architectures as Latent Variable Models, , EPFL, 2025 |
[URL] |
| On feature representations for marmoset vocal communication analysis, , , , and , in: Bioacoustics: The International Journal of Animal Sound and its Recording:1-15, 2025 |
[DOI] [URL] |
| Towards Leveraging Sequential Structure in Animal Vocalizations, and , in: Neural Information Processing Systems workshop: AI for Non-Human Animal Communication, 2025 |
|
| Transferability of Learnt Speech Representations for Decoding Non-Human Vocal Communication, , Ecole Polytechnique Fédérale de Lausanne, 2025 |
|
2024
| Beyond bigrams: call sequencing in the common marmoset (Callithrix jacchus) vocal system, , , , , and , in: Royal Society Open Science, 11(11), 2024 |
[URL] |
| Feature Representations for Automatic Meerkat Vocalization Classification, , , and , in: 4th International Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots, 2024 |
|
| Nonparametric Variational Regularisation of Pretrained Transformers, and , in: First conference on Language Modelling, 2024 |
[URL] |
| On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis, and , in: 4th International Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots, 2024 |
|
| Speech prosody enhances the neural processing of syntax, , , , and , in: Communications Biology, 7(748), 2024 |
[DOI] [URL] |
| Surprisal From Language Models Can Predict ERPs in Processing Predicate-Argument Structures Only if Enriched by an Agent Preference Principle, , , , , and , in: Neurobiology of Language, 5(1):167--200, 2024 |
[DOI] [URL] |
2023
| A VAE for Transformers with Nonparametric Variational Information Bottleneck, and , in: The Eleventh International Conference on Learning Representations, 2023 |
[URL] |
| Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?, and , in: Proceedings of Interspeech, 2023 |
|
| Inducing Meaningful Units from Character Sequences with Dynamic Capacity Slot Attention, and , in: Transactions on Machine Learning Research, 2023 |
[URL] |
| Learning to Abstract with Nonparametric Variational Information Bottleneck, , and , in: The 2023 Conference on Empirical Methods in Natural Language Processing, 2023 |
[URL] |
| Loose and Tight: Creative Formation but Rigid Use of Nominal Compounds in Conspiracist Texts, , and , in: The Journal of Creative Behavior, 2023 |
| Nonparametric Variational Regularisation of Pretrained Transformers, and , in: ArXiv, 2023 |
[DOI] [URL] |
| Using Commercial ASR Solutions to Assess Reading Skills in Children: A Case Report, , , , , and , in: Proceedings of Interspeech, pages 4573-4577, 2023 |
[DOI] [URL] |
2022
| A Variational AutoEncoder for Transformers with Nonparametric Variational Information Bottleneck, and , in: arxiv, 2022 |
[DOI] [URL] |
| HyperMixer: An MLP-based Green AI Alternative to Transformers, , , , , , and , in: arxiv, 2022 |
| Unsupervised Voice Activity Detection by Modeling Source and System Information using Zero Frequency Filtering, , and , in: Proceedings of Interspeech, 2022 |
|