Zobrazeno 1 - 10
of 248
pro vyhledávání: '"Paul Gauthier"'
Originating in game theory, Shapley values are widely used for explaining a machine learning model's prediction by quantifying the contribution of each feature's value to the prediction. This requires a scalar prediction as in binary classification,
Externí odkaz:
http://arxiv.org/abs/2408.01382
Fusing outputs from automatic speaker verification (ASV) and spoofing countermeasure (CM) is expected to make an integrated system robust to zero-effort imposters and synthesized spoofing attacks. Many score-level fusion methods have been proposed, b
Externí odkaz:
http://arxiv.org/abs/2406.10836
Most recent speech privacy efforts have focused on anonymizing acoustic speaker attributes but there has not been as much research into protecting information from speech content. We introduce a toy problem that explores an emerging type of privacy c
Externí odkaz:
http://arxiv.org/abs/2401.03936
Publikováno v:
Therapeutic Advances in Infectious Disease, Vol 6 (2019)
Background: Cervical spinal epidural abscess (CSEA) is a localized infection between the thecal sac and cervical spinal column which may result in neurological deficit and death if inadequately treated. Two treatment options exist: medical management
Externí odkaz:
https://doaj.org/article/adc2d985d42445d281ea4d0cada5ba90
Privacy in speech and audio has many facets. A particularly under-developed area of privacy in this domain involves consideration for information related to content and context. Speech content can include words and their meaning or even stylistic mar
Externí odkaz:
http://arxiv.org/abs/2301.08925
Autor:
Brian R. Zutta, Phillip W. Rundel, Sassan Saatchi, Jorge D. Casana, Paul Gauthier Gauthier, Aldo Soto, Yessenia Velazco, Wolfgang Buermann
Publikováno v:
Revista Peruana de Biología, Vol 19, Iss 2, Pp 205-212 (2012)
Polylepis woodlands are a vital resource for preserving biodiversity and hydrological functions, which will be altered by climate change and challenge the sustainability of local human communities. However, these highaltitude Andean ecosystems are be
Externí odkaz:
https://doaj.org/article/6208688c61a4446ab029aa723c7e8c7d
Autor:
Noé, Paul-Gauthier, Miao, Xiaoxiao, Wang, Xin, Yamagishi, Junichi, Bonastre, Jean-François, Matrouf, Driss
The use of modern vocoders in an analysis/synthesis pipeline allows us to investigate high-quality voice conversion that can be used for privacy purposes. Here, we propose to transform the speaker embedding and the pitch in order to hide the sex of t
Externí odkaz:
http://arxiv.org/abs/2211.16065
Autor:
Tomashenko, Natalia, Srivastava, Brij Mohan Lal, Wang, Xin, Vincent, Emmanuel, Nautsch, Andreas, Yamagishi, Junichi, Evans, Nicholas, Patino, Jose, Bonastre, Jean-François, Noé, Paul-Gauthier, Todisco, Massimiliano
The VoicePrivacy Challenge aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of
Externí odkaz:
http://arxiv.org/abs/2205.07123
Autor:
Williams, Jennifer, Yamagishi, Junichi, Noe, Paul-Gauthier, Botinhao, Cassia Valentini, Bonastre, Jean-Francois
In this paper, we discuss an important aspect of speech privacy: protecting spoken content. New capabilities from the field of machine learning provide a unique and timely opportunity to revisit speech content protection. There are many different app
Externí odkaz:
http://arxiv.org/abs/2110.06760
Autor:
Noé, Paul-Gauthier, Nautsch, Andreas, Matrouf, Driss, Bousquet, Pierre-Michel, Bonastre, Jean-François
Attribute-driven privacy aims to conceal a single user's attribute, contrary to anonymisation that tries to hide the full identity of the user in some data. When the attribute to protect from malicious inferences is binary, perfect privacy requires t
Externí odkaz:
http://arxiv.org/abs/2110.05840