Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Xiaoxiao Miao"'
Publikováno v:
IEEE Open Journal of Signal Processing, Vol 5, Pp 257-265 (2024)
Speaker anonymization is the task of modifying a speech recording such that the original speaker cannot be identified anymore. Since the first Voice Privacy Challenge in 2020, along with the release of a framework, the popularity of this research top
Externí odkaz:
https://doaj.org/article/99609239c7144431a553f28112d472ff
Publikováno v:
Electronics Letters, Vol 58, Iss 2, Pp 82-85 (2022)
Abstract Data augmentation is an essential technique for building a high‐robustness speaker recognition system. this letter proposes a novel on‐the‐fly data augmentation strategy called GuidedMix. It significantly increases augmented data fidel
Externí odkaz:
https://doaj.org/article/f3b422167af54765a548ff7f0b73a6d4
Publikováno v:
IEEE Access, Vol 7, Pp 94917-94930 (2019)
In this paper, the girth distribution of the Tanner’s (3, 17)-regular quasi-cyclic LDPC (QC-LDPC) codes with code length $17p$ is determined, where $p$ is a prime and $p \equiv 1~(\bmod ~51)$ . By analyzing their cycle structure, five equivalent ty
Externí odkaz:
https://doaj.org/article/94185c07633247ff8a91d2071a5dadd1
Autor:
Paul-Gauthier Noé, Xiaoxiao Miao, Xin Wang, Junichi Yamagishi, Jean-François Bonastre, Driss Matrouf
This is the pretrained models for paper "Hiding speaker's sex in speech using zero-evidence speaker representation in an analysis/synthesis pipeline"http://arxiv.org/abs/2211.16065 The authors arePaul-Gauthier Noé, Xiaoxiao Miao, Xin Wang,Junichi Ya
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e737b11cca0620b5a51569fad9dd302f
Autor:
Paul-Gauthier Noé, Xiaoxiao Miao, Xin Wang, Junichi Yamagishi, Jean-François Bonastre, Driss Matrouf
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:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::515fb11ab676a775a00bcf09e6f10375
http://arxiv.org/abs/2211.16065
http://arxiv.org/abs/2211.16065
Publikováno v:
Circuits, Systems, and Signal Processing. 40:3621-3638
This paper proposes novel features for automated language and dialect identification that aim to improve discriminative power by ensuring that each element of the feature vector has a normalised contribution to inter-class variance. The method firstl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c45a1fb4c6e76010eb7b5fa04c73092
https://doi.org/10.1007/s00034-020-01641-1
https://doi.org/10.1007/s00034-020-01641-1
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Probabilistic linear discriminant analysis (PLDA) or cosine similarity have been widely used in traditional speaker verification systems as back-end techniques to measure pairwise similarities. To make better use of multiple enrollment utterances, we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f9d3713c07a7b1fd4ff17534c856c22f
https://doi.org/10.1109/icassp43922.2022.9746688
https://doi.org/10.1109/icassp43922.2022.9746688
This is thepretrained models and anonymized speaker vectorsfrom two of our papers: "Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Models," (Odyssey2022) https://arxiv.org/abs/2202.13097 "Analyzing Language-Inde
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::408b4e25d41077d9f10f985196e9a17c
In our previous work, we proposed a language-independent speaker anonymization system based on self-supervised learning models. Although the system can anonymize speech data of any language, the anonymization was imperfect, and the speech content of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::775695c7874b640e4ac1f16ee1843d42
http://arxiv.org/abs/2203.14834
http://arxiv.org/abs/2203.14834
Publikováno v:
2021 17th International Conference on Computational Intelligence and Security (CIS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d48de03c97f0c92cb4a72d9f990f14e5
https://doi.org/10.1109/cis54983.2021.00099
https://doi.org/10.1109/cis54983.2021.00099