Zobrazeno 1 - 10
of 4 049
pro vyhledávání: '"A. Carbonneau"'
Discovering a lexicon from unlabeled audio is a longstanding challenge for zero-resource speech processing. One approach is to search for frequently occurring patterns in speech. We revisit this idea with DUSTED: Discrete Unit Spoken-TErm Discovery.
Externí odkaz:
http://arxiv.org/abs/2408.14390
Real world deployments of word alignment are almost certain to cover both high and low resource languages. However, the state-of-the-art for this task recommends a different model class depending on the availability of gold alignment training data fo
Externí odkaz:
http://arxiv.org/abs/2407.12881
Grammatical Error Detection (GED) methods rely heavily on human annotated error corpora. However, these annotations are unavailable in many low-resource languages. In this paper, we investigate GED in this context. Leveraging the zero-shot cross-ling
Externí odkaz:
http://arxiv.org/abs/2407.11854
We introduce UPose3D, a novel approach for multi-view 3D human pose estimation, addressing challenges in accuracy and scalability. Our method advances existing pose estimation frameworks by improving robustness and flexibility without requiring direc
Externí odkaz:
http://arxiv.org/abs/2404.14634
Autor:
Dib, Abdallah, Hafemann, Luiz Gustavo, Got, Emeline, Anderson, Trevor, Fadaeinejad, Amin, Cruz, Rafael M. O., Carbonneau, Marc-Andre
Reconstructing an avatar from a portrait image has many applications in multimedia, but remains a challenging research problem. Extracting reflectance maps and geometry from one image is ill-posed: recovering geometry is a one-to-many mapping problem
Externí odkaz:
http://arxiv.org/abs/2312.13091
Audio diffusion models can synthesize a wide variety of sounds. Existing models often operate on the latent domain with cascaded phase recovery modules to reconstruct waveform. This poses challenges when generating high-fidelity audio. In this paper,
Externí odkaz:
http://arxiv.org/abs/2311.08667
Voice conversion aims to transform source speech into a different target voice. However, typical voice conversion systems do not account for rhythm, which is an important factor in the perception of speaker identity. To bridge this gap, we introduce
Externí odkaz:
http://arxiv.org/abs/2307.06040
Autor:
Martin Schröder, Martin Renatus, Xiaoyou Liang, Fabian Meili, Thomas Zoller, Sandrine Ferrand, Francois Gauter, Xiaoyan Li, Frederic Sigoillot, Scott Gleim, Therese-Marie Stachyra, Jason R. Thomas, Damien Begue, Maryam Khoshouei, Peggy Lefeuvre, Rita Andraos-Rey, BoYee Chung, Renate Ma, Benika Pinch, Andreas Hofmann, Markus Schirle, Niko Schmiedeberg, Patricia Imbach, Delphine Gorses, Keith Calkins, Beatrice Bauer-Probst, Magdalena Maschlej, Matt Niederst, Rob Maher, Martin Henault, John Alford, Erik Ahrne, Luca Tordella, Greg Hollingworth, Nicolas H. Thomä, Anna Vulpetti, Thomas Radimerski, Philipp Holzer, Seth Carbonneau, Claudio R. Thoma
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-5 (2024)
Externí odkaz:
https://doaj.org/article/1168651eade84aa68bb9c377c9befbde
Publikováno v:
Disabilities, Vol 4, Iss 3, Pp 525-538 (2024)
To improve inclusion of persons with disabilities (PWD), it is important to create suitable physical and social environments. This can be done by improving awareness about disability, specifically for employees working in the service and cultural sec
Externí odkaz:
https://doaj.org/article/32e66ea4120b45a8abbae20b61389dce
Autor:
Carbonneau, Élise, Dumas, Audrée-Anne, Drouin Rousseau, Sophie, Lavigne, Geneviève, Carbonneau, Noémie
Publikováno v:
In Journal of Nutrition Education and Behavior July 2024 56(7):428-441