Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Olvera, Michel"'
Multimodal large language models have fueled progress in image captioning. These models, fine-tuned on vast image datasets, exhibit a deep understanding of semantic concepts. In this work, we show that this ability can be re-purposed for audio captio
Externí odkaz:
http://arxiv.org/abs/2410.05997
Audio-text models trained via contrastive learning offer a practical approach to perform audio classification through natural language prompts, such as "this is a sound of" followed by category names. In this work, we explore alternative prompt templ
Externí odkaz:
http://arxiv.org/abs/2409.13676
Publikováno v:
DCASE, Oct 2024, Tokyo, Japan
Machine listening systems often rely on fixed taxonomies to organize and label audio data, key for training and evaluating deep neural networks (DNNs) and other supervised algorithms. However, such taxonomies face significant constraints: they are co
Externí odkaz:
http://arxiv.org/abs/2409.11746
Current state-of-the-art audio analysis systems rely on pre-trained embedding models, often used off-the-shelf as (frozen) feature extractors. Choosing the best one for a set of tasks is the subject of many recent publications. However, one aspect of
Externí odkaz:
http://arxiv.org/abs/2312.14005
Publikováno v:
28th European Signal Processing Conference (EUSIPCO), Jan 2021, Amsterdam, Netherlands
Ambient sound scenes typically comprise multiple short events occurring on top of a somewhat stationary background. We consider the task of separating these events from the background, which we call foreground-background ambient sound scene separatio
Externí odkaz:
http://arxiv.org/abs/2005.07006
Autor:
Pariente, Manuel, Cornell, Samuele, Cosentino, Joris, Sivasankaran, Sunit, Tzinis, Efthymios, Heitkaemper, Jens, Olvera, Michel, Stöter, Fabian-Robert, Hu, Mathieu, Martín-Doñas, Juan M., Ditter, David, Frank, Ariel, Deleforge, Antoine, Vincent, Emmanuel
This paper describes Asteroid, the PyTorch-based audio source separation toolkit for researchers. Inspired by the most successful neural source separation systems, it provides all neural building blocks required to build such a system. To improve rep
Externí odkaz:
http://arxiv.org/abs/2005.04132
Autor:
Olvera, Michel
Publikováno v:
Computer Science [cs]. Université de Lorraine, 2022. English. ⟨NNT : 2022LORR0324⟩
From industry to general interest applications, computational analysis of sound scenes and events allows us to interpret the continuous flow of everyday sounds. One of the main degradations encountered when moving from lab conditions to the real worl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______165::65c39d254fbd8d3e69738665ec3c061d
https://hal.univ-lorraine.fr/tel-04087756
https://hal.univ-lorraine.fr/tel-04087756
Publikováno v:
ICASSP 2022-IEEE International Conference on Acoustics, Speech and Signal Processing
ICASSP 2022-IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapore, Singapore. ⟨10.1109/ICASSP43922.2022.9747540⟩
ICASSP 2022-IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapore, Singapore. ⟨10.1109/ICASSP43922.2022.9747540⟩
International audience; Acoustic scene classification systems face performance degradation when trained and tested on data recorded by different devices. Unsupervised domain adaptation methods have been studied to reduce the impact of this mismatch.
Publikováno v:
DCASE 2021-6th Workshop on Detection and Classification of Acoustic Scenes and Events
DCASE 2021-6th Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2021, Virtual, Spain
DCASE 2021-6th Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2021, Virtual, Spain
International audience; In this paper we provide two methods that improve the detection of sound events in domestic environments. First, motivated by the broad categorization of domestic sounds as foreground or background events according to their sp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::9e42052ad5fd710a1a2b50d212a231c0
https://hal.inria.fr/hal-03387778/file/DCASE_Workshop_2021.pdf
https://hal.inria.fr/hal-03387778/file/DCASE_Workshop_2021.pdf
Autor:
Cornell, Samuele, Olvera, Michel, Pariente, Manuel, Pepe, Giovanni, Principi, Emanuele, Gabrielli, Leonardo, Squartini, Stefano
Publikováno v:
DCASE 2020-5th Workshop on Detection and Classification of Acoustic Scenes and Events
DCASE 2020-5th Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2020, Virtual, Japan
DCASE 2020-5th Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2020, Virtual, Japan
International audience; In this paper, we propose several methods for improving Sound Event Detection systems performance in the context of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 Task 4 challenge. Our main contrib
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c701f09d2e903c45d613c0e639563a0a
https://hal.inria.fr/hal-02962911
https://hal.inria.fr/hal-02962911