Half-Truth: A Partially Fake Audio Detection Dataset

Yi, Jiangyan; Bai, Ye; Tao, Jianhua; Tian, Zhengkun; Wang, Chenglong; Wang, Tao; Fu, Ruibo

doi:10.48550/arxiv.2104.03617

Cited by 2 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gao et al [208] presented a novel method for the detection of audio deep-fake that used long-range spectrotemporal modulation features. Using a 2D discrete cosine transform (DCT) on a log-mel spectrogram, the system outperforms traditional feature methods such as CQCC [209]. The model leverages spectrum augmentation and feature normalisation to reduce overfitting, resulting in a stateof-the-art system for spoof detection and demonstrating its effectiveness on two external datasets.…”

Section: ) Methods Using Handcrafted Featuresmentioning

confidence: 99%

A Survey on the Detection and Impacts of Deepfakes in Visual, Audio, and Textual Formats

Mubarak,

Alsboui,

Alshaikh

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In the rapidly evolving digital landscape, the generation of fake visual, audio, and textual content poses a significant threat to society's trust, political stability, and integrity of information. The generation process has been enhanced and simplified using Artificial Intelligence techniques, which have been termed deepfake. Although significant attention has been paid to visual and audio deepfakes, there is also a burgeoning need to consider text-based deepfakes. Due to advancements in natural language processing and large language models, the potential of manipulating textual content to reshape online discourse and misinformation has increased. This study comprehensively examines the multifaceted nature and impacts of deep-fake-generated media. This work explains the broad implications of deepfakes in social, political, economic, and technological domains. State-of-the-art detection methodologies for all types of deepfake are critically reviewed, highlighting the need for unified, real-time, adaptable, and generalised solutions. As the challenges posed by deepfakes intensify, this study underscores the importance of a holistic approach that intertwines technical solutions with public awareness and legislative action. By providing a comprehensive overview and establishing a framework for future exploration, this study seeks to assist researchers, policymakers, and practitioners in navigating the complexities of deepfake phenomena.

show abstract

Section: ) Methods Using Handcrafted Featuresmentioning

confidence: 99%

A Survey on the Detection and Impacts of Deepfakes in Visual, Audio, and Textual Formats

Mubarak,

Alsboui,

Alshaikh

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The replace part is semantically complete, guaranteed by text alignment techniques. This way is similar to the generation process of HAD dataset [15].…”

Section: Clean Fake Audios Generationmentioning

confidence: 97%

“…For the datasets used to spoof the human auditory system, FoR dataset [13] contains fake audios from 7 open resources and real audios from 4 resources. HAD dataset [15] is designed for partially fake audio detection, generated by manipulated the original utterances with genuine or synthesized audio segments. WaveFake [14] collects ten sample sets from six different network architectures across two languages.…”

Section: Related Workmentioning

confidence: 99%

FAD: A Chinese Dataset for Fake Audio Detection

Ma¹,

Yi²,

Wang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Fake audio detection is a growing concern and some relevant datasets have been designed for research. But there is no standard public Chinese dataset under additive noise conditions. In this paper, we aim to fill in the gap and design a Chinese fake audio detection dataset (FAD) for studying more generalized detection methods. Twelve mainstream speech generation techniques are used to generate fake audios. To simulate the real-life scenarios, three noise datasets are selected for noisy adding at five different signal noise ratios. FAD dataset can be used not only for fake audio detection, but also for detecting the algorithms of fake utterances for audio forensics. Baseline results are presented with analysis. The results that show fake audio detection methods with generalization remain challenging. The FAD dataset is publicly available 1 .Recently, fake audio detection is not limited to ASV system, but also starts to focus on real-life scenarios. The first audio deep synthesis detection challenge [12] (ADD 2022) focuses on challenging situations, including low-quality fake audio and partially fake audio detection. More datasets are constrcted by deep-learning speech techniques, such as: FoR [13], WaveFake [14], and HAD [15] datasets.These above-mentioned datasets facilitate the progress of the fake audio detection research. However, in practical applications, audios on social media come in many languages with noisy background and the type of fake audio may be unknown to the model. Those various factors greatly influence the performance of the detection models. The generalization of the detection models is still an urgent need to address. Specifically, the generalization includes generalization to unknown types and robustness to noise and other factors. Most datasets focus on the evaluation of the former aspect, 1 https://zenodo.org/record/6635521#.Ysjq4nZBw2x

show abstract

Half-Truth: A Partially Fake Audio Detection Dataset

Cited by 2 publications

References 25 publications

A Survey on the Detection and Impacts of Deepfakes in Visual, Audio, and Textual Formats

A Survey on the Detection and Impacts of Deepfakes in Visual, Audio, and Textual Formats

FAD: A Chinese Dataset for Fake Audio Detection

Contact Info

Product

Resources

About