Výsledky vyhledávání - "Voice transformation"

Akademický článek

Depersonalization of Speech Using Speaker-Specific Transform Based on Long-Term Spectrum

Autor: M. Rujzl, M. Sigmund

Publikováno v: Radioengineering, Vol 32, Iss 4, Pp 523-530 (2023)

This paper introduces a novel approach for hiding personal information in speech signals. The proposed approach applied a transform warping function, which is obtained from a long-term linear prediction spectrum individually for each speaker. The dep

Externí odkaz: https://doaj.org/article/ab33191388e44970a2f33ab2acc56e97

Zobrazit plný text záznamu

Akademický článek

Voice Transformation Using Two-Level Dynamic Warping and Neural Networks

Autor: Al-Waled Al-Dulaimi, Todd K. Moon, Jacob H. Gunther

Publikováno v: Signals, Vol 2, Iss 3, Pp 456-474 (2021)

Voice transformation, for example, from a male speaker to a female speaker, is achieved here using a two-level dynamic warping algorithm in conjunction with an artificial neural network. An outer warping process which temporally aligns blocks of spee

Externí odkaz: https://doaj.org/article/dc2de8b98b7a4f07922eac17b2e8ac4b

Zobrazit plný text záznamu

Hearing protection and communication in high noise environments using vibration sensing and neural network voice transformation

Autor: Willem M. Beltman, Hector Cordourier, Jonathan Huang, Hong Lu, Paulo Lopez Meyer, Lama Nachman

Publikováno v: INTER-NOISE and NOISE-CON Congress and Conference Proceedings. 263:5027-5037

In the United States alone, there are more than 9 million workers who are exposed to high levels of noise (> 85 dBA) that require hearing protection. Not only is there a risk of hearing damage due to these high noise levels, but it also prevents comm

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6c9fbfb6a0c83116f36d49a0d81ab0b9
https://doi.org/10.3397/in-2021-2925

Zobrazit plný text záznamu

Voice Transformation Using Two-Level Dynamic Warping and Neural Networks

Autor: Jacob H. Gunther, Al-Waled Al-Dulaimi, Todd K. Moon

Publikováno v: Signals, Vol 2, Iss 28, Pp 456-474 (2021)
Signals
Volume 2
Issue 3
Pages 28-474

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::46c81c37e874badb2fad615dfbcd43a1
https://doi.org/10.3390/signals2030028

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

The shallow of your smile: the ethics of expressive vocal deep-fakes

Autor: Guillaume Vaiva, Jean-Julien Aucouturier, Nadia Guerouaou

Publikováno v: Philosophical Transactions of the Royal Society B: Biological Sciences
Philosophical Transactions of the Royal Society B: Biological Sciences, Royal Society, The, 2021, 377 (20210083), pp.1-5. ⟨10.1098/rstb.2021.0083⟩
Philosophical Transactions of the Royal Society B: Biological Sciences, Royal Society, The, 2022, 377 (1841), ⟨10.1098/rstb.2021.0083⟩
Philosophical Transactions of the Royal Society B: Biological Sciences, 2021, 377 (20210083), pp.1-5. ⟨10.1098/rstb.2021.0083⟩

Rapid technological advances in artificial intelligence are creating opportunities for real-time algorithmic modulations of a person’s facial and vocal expressions, or ‘deep-fakes’. These developments raise unprecedented societal and ethical qu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::872ec3a9b7b6d1768731c1c5d5677d64
https://hal.archives-ouvertes.fr/hal-03455023/document

Zobrazit plný text záznamu

Exploring Disentanglement with Multilingual and Monolingual VQ-VAE

Autor: Jason Fong, Junichi Yamagishi, Jennifer Williams, Erica Cooper

Publikováno v: 11th ISCA Speech Synthesis Workshop (SSW 11).

This work examines the content and usefulness of disentangled phone and speaker representations from two separately trained VQ-VAE systems: one trained on multilingual data and another trained on monolingual data. We explore the multi- and monolingua

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de065fe391f54c44ea276cf3645bbdcc
https://doi.org/10.21437/ssw.2021-22

Zobrazit plný text záznamu

Development of a Two-Level Warping Algorithm and Its Application to Speech Signal Processing

Autor: Al-Dulaimi, Al-Waled H.

Publikováno v: All Graduate Theses and Dissertations

In many different fields there are signals that need to be aligned or “warped” in order to measure the similarity between them. When two time signals are compared, or when a pattern is sought in a larger stream of data, it may be necessary to war

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d77b627c9737a783ce697dcf8d211f93
https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=9172&context=etd

Zobrazit plný text záznamu

Exploiting Voice Transformation to Promote Interaction in Virtual Environments

Autor: Isabelle Viaud-Delmon, Trami Nguyen, Vincent Isnard

Publikováno v: 2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)
IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)
IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), Mar 2021, Virtual event, United States. ⟨10.1109/vrw52623.2021.00021⟩
VR Workshops

International audience; We propose a new type of interaction dedicated to virtual reality (VR). We have designed a futuristic scenario promoting a dialogue with a humanoid. The participant is submitted to a reverse Turing test and has to answer quest

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a4b468a1bec8aa41d7b9446754e9654c
https://hal.archives-ouvertes.fr/hal-03230293

Zobrazit plný text záznamu

Akademický článek

Spectral Envelope Transformation in Singing Voice for Advanced Pitch Shifting

Autor: José L. Santacruz, Lorenzo J. Tardón, Isabel Barbancho, Ana M. Barbancho

Publikováno v: Applied Sciences, Vol 6, Iss 11, p 368 (2016)

The aim of the present work is to perform a step towards more natural pitch shifting techniques in singing voice for its application in music production and entertainment systems. In this paper, we present an advanced method to achieve natural modifi

Externí odkaz: https://doaj.org/article/5f0999b4359248ed8efff8e615f5df7d

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání