Publications of project armasuisse
2024
| Fine-tuning Self-Supervised Models For Language Identification Using Orthonormal Constraint, , , , , , and , in: Proceedings of the 49th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP), pages 11921-11925, 2024 |
[DOI] |
| Normalizing Flows for Speaker and Language Recognition Backend, , , , and , in: Odyssey 2024: The Speaker and Language Recognition Workshop, 2024 |
|
| Speech and Language Recognition with Low-rank Adaptation of Pretrained Models, , , , and , in: Interspeech 2024, pages 2825--2829, 2024 |
[DOI] [URL] |
2023
| An Automatic Speaker Clustering Pipeline for the Air Traffic Communication Domain, , , , , , and , in: Aerospace, 10(10):876, 2023 |
[DOI] [URL] |
| Confidence Matters : Applications to Semantic Segmentation, , École polytechnique fédérale de Lausanne, 2023 |
[DOI] |
2022
| Borrowing from yourself: Faster future video segmentation with partial channel update, and , in: International Conference on Pattern Recognition, 2022 |
|
| Paumer: Patch Pausing Transformer for Semantic Segmentation, , and , in: 33th British Machine Vision Conference 2022, London, UK, 21 - 24 November 2022, 2022 |
|
2021
| Test time Adaptation through Perturbation Robustness, and , Idiap-RR-17-2021 |
| Test time Adaptation through Perturbation Robustness, and , in: Workshop on Distribution Shifts, 35th Conference on Neural Information Processing Systems (NeurIPS 2021), 2021 |
|
| Uncertainty Reduction for Model Adaptation in Semantic Segmentation, and , in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 |
|
2020
| Real-Time Segmentation Networks should be Latency Aware, and , in: Asian Conference on Computer Vision, 2020 |
|
2016
| "Can you hear me now?" --- Automatic assessment of background noise intrusiveness and speech intelligibility in telecommunications, , Sciences et Techniques de l’Ingénieur (STI), 2016 |
[DOI] |
2015
| Incremental Syllable-Context Phonetic Vocoding, , , , and , Idiap-RR-05-2015 |
|
| Objective Intelligibility Assessment of Text-to-Speech Systems Through Utterance Verification, , , and , Idiap-RR-06-2015 |
|
| Objective Intelligibility Assessment of Text-to-Speech Systems Through Utterance Verification, , , and , in: Proceedings of Interspeech, Dresden, Germany, pages 3501-3505, 2015 |
[URL] |
| Objective Speech Intelligibility Assessment through Comparison of Phoneme Class Conditional Probability Sequences, , and , in: 40th IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, pages 4924-4928, 2015 |
[DOI] |
| Phonological vocoding using artificial neural networks, , and , Idiap-RR-04-2015 |
|
| Phonological Vocoding Using Artificial Neural Networks, , and , in: IEEE 40th International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, pages 4844-4848, IEEE, 2015 |
[DOI] |
2014