Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Research data Set de datos (Dataset)

Audio Deepfakes and Synthetic Media: Reading list [DATASET]

  • San Segundo Fernández, Eugenia
  • López Jareño, Aurora
  • Rodríguez Sánchez, Vega
[EN] This is a curated reading list on audio deepfakes and synthetic media; that is, an expert-selected guide to the most relevant publications and resources on this topic published in recent years. The curators reviewed a wide range of sources, selected the most relevant and reliable ones, and organized them according to criteria such as the type of deepfake, modality, language, and intended audience (specialized or general), among others., [ES] Esta es una lista de lecturas seleccionadas sobre deepfakes de audio y contenidos digitales sintéticos; es decir, una guía elaborada por expertos que reúne algunas de las publicaciones y recursos más relevantes sobre este tema aparecidos en los últimos años. Para elaborarla, revisamos una amplia variedad de fuentes y seleccionamos aquellas que consideramos más relevantes y fiables. Posteriormente, organizamos los materiales según distintos criterios, como el tipo de deepfake, la modalidad, el idioma y el público objetivo —especializado o general—, entre otros., This work is part of the research project How deep(fake) is your voice? Understanding the linguistic foundations of deepfakes (grant PID2021-124995OA-I00 funded by MICIU/AEI/ 10.13039/501100011033 and by ERDF/EU) and the project WAV: The WAves (and wrinkles) of our Voice (grant PID2024-161495OB-I00 funded by MICIU/AEI/ 10.13039/501100011033 and by ERDF/EU)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

A qualitative systematic review of intra-speaker variation in the human voice

  • San Segundo Fernández, Eugenia
  • Delgado, Jonathan
Audio deepfake detection is essential for addressing societal challenges such as differentiating real news from fake content or authenticating voice recordings in legal contexts. However, identifying whether a voice is human or AI-generated requires knowing which characteristics to examine, and the choice of voice features for this task is relatively unguided. This justifies the systematic review presented in this paper. Hypothesizing that human voices exhibit more intra-speaker variation than deepfakes, the aim of this review has been to summarize and analyze the published studies on the topic of intra-speaker variation in human voice. A systematic search was conducted in Web of Science, the Cochrane Library, and the electronic database of the International Journal of Speech Language and the Law, initially identifying 305 studies. After removing duplicates and applying inclusion/exclusion criteria, 36 articles were selected for analysis. Findings highlight speaking style as a major factor in intra-speaker variation affecting various acoustic parameters. This review suggests that experts may prioritize features that show higher within-speaker variation, while noting that their utility for deepfake detection must be verified on deepfake datasets., We thank the grant PID2021-124995OA-I00 funded by MICIU/AEI/10.13039/501100011033 and by ERDF/EU, Peer reviewed