中文
相关论文

相关论文: Leveraging Mixture of Experts for Improved Speech …

200 篇论文

Deepfakes are AI-generated media in which an image or video has been digitally modified. The advancements made in deepfake technology have led to privacy and security issues. Most deepfake detection techniques rely on the detection of a…

计算机视觉与模式识别 · 计算机科学 2023-10-09 Sneha Muppalla , Shan Jia , Siwei Lyu

Generalization is a main issue for current audio deepfake detectors, which struggle to provide reliable results on out-of-distribution data. Given the speed at which more and more accurate synthesis methods are developed, it is very…

声音 · 计算机科学 2024-07-02 Alessandro Pianese , Davide Cozzolino , Giovanni Poggi , Luisa Verdoliva

Automatic speech quality assessment plays a crucial role in the development of speech synthesis systems, but existing models exhibit significant performance variations across different granularity levels of prediction tasks. This paper…

声音 · 计算机科学 2025-07-09 Xintong Hu , Yixuan Chen , Rui Yang , Wenxiang Guo , Changhao Pan

This paper reviews the state-of-the-art in deepfake generation and detection, focusing on modern deep learning technologies and tools based on the latest scientific advancements. The rise of deepfakes, leveraging techniques like Variational…

密码学与安全 · 计算机科学 2025-01-14 Arash Dehghani , Hossein Saberi

The growing prevalence of speech deepfakes has raised serious concerns, particularly in real-world scenarios such as telephone fraud and identity theft. While many anti-spoofing systems have demonstrated promising performance on…

音频与语音处理 · 电气工程与系统科学 2026-05-12 Tong Zhang , Yihuan Huang , Yanzhen Ren

Pioneering advancements in artificial intelligence, especially in genAI, have enabled significant possibilities for content creation, but also led to widespread misinformation and false content. The growing sophistication and realism of…

人工智能 · 计算机科学 2024-11-14 Dinesh Srivasthav P , Badri Narayan Subudhi

This paper is concerned with the task of speaker verification on audio with multiple overlapping speakers. Most speaker verification systems are designed with the assumption of a single speaker being present in a given audio segment.…

音频与语音处理 · 电气工程与系统科学 2023-04-10 Jenthe Thienpondt , Nilesh Madhu , Kris Demuynck

Recent advances in audio generation led to an increasing number of deepfakes, making the general public more vulnerable to financial scams, identity theft, and misinformation. Audio deepfake detectors promise to alleviate this issue, with…

Generative AI advances rapidly, allowing the creation of very realistic manipulated video and audio. This progress presents a significant security and ethical threat, as malicious users can exploit DeepFake techniques to spread…

多媒体 · 计算机科学 2025-06-09 Marcel Klemt , Carlotta Segna , Anna Rohrbach

Generative deep learning models are able to create realistic audio and video. This technology has been used to impersonate the faces and voices of individuals. These ``deepfakes'' are being used to spread misinformation, enable scams,…

人工智能 · 计算机科学 2023-06-06 Guy Frankovits , Yisroel Mirsky

Many approaches can derive information about a single speaker's identity from the speech by learning to recognize consistent characteristics of acoustic parameters. However, it is challenging to determine identity information when there are…

音频与语音处理 · 电气工程与系统科学 2020-08-07 Hyewon Han , Soo-Whan Chung , Hong-Goo Kang

Recent advances in Text-to-Speech (TTS) systems have substantially increased the realism of synthetic speech, raising new challenges for audio deepfake detection. This work presents a comparative evaluation of three state-of-the-art TTS…

The advancements in generative AI have enabled the improvement of audio synthesis models, including text-to-speech and voice conversion. This raises concerns about its potential misuse in social manipulation and political interference, as…

密码学与安全 · 计算机科学 2024-09-12 Hong-Hanh Nguyen-Le , Van-Tuan Tran , Dinh-Thuc Nguyen , Nhien-An Le-Khac

Deepfake is a widely used technology employed in recent years to create pernicious content such as fake news, movies, and rumors by altering and substituting facial information from various sources. Given the ongoing evolution of deepfakes…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Ruchika Sharma , Rudresh Dwivedi

As synthetic media, including video, audio, and text, become increasingly indistinguishable from real content, the risks of misinformation, identity fraud, and social manipulation escalate. This survey traces the evolution of deepfake…

计算机视觉与模式识别 · 计算机科学 2025-04-04 Ping Liu , Qiqi Tao , Joey Tianyi Zhou

Generative AI (Gen-AI) deepfakes pose a rapidly evolving threat to biometric authentication, yet a significant gap exists between expert understanding of these risks and public perception. This disconnection creates critical vulnerabilities…

人机交互 · 计算机科学 2025-06-10 Shijing He , Yaxiong Lei , Zihan Zhang , Yuzhou Sun , Shujun Li , Chi Zhang , Juan Ye

Deep Learning has been successfully applied in diverse fields, and its impact on deepfake detection is no exception. Deepfakes are fake yet realistic synthetic content that can be used deceitfully for political impersonation, phishing,…

计算机视觉与模式识别 · 计算机科学 2024-11-13 Ammarah Hashmi , Sahibzada Adil Shahzad , Chia-Wen Lin , Yu Tsao , Hsin-Min Wang

While the technologies empowering malicious audio deepfakes have dramatically evolved in recent years due to generative AI advances, the same cannot be said of global research into spoofing (deepfake) countermeasures. This paper highlights…

音频与语音处理 · 电气工程与系统科学 2026-03-16 Héctor Delgado , Giorgio Ramondetti , Emanuele Dalmasso , Gennady Karvitsky , Daniele Colibro , Haydar Talib

Speech synthesis technology has brought great convenience, while the widespread usage of realistic deepfake audio has triggered hazards. Malicious adversaries may unauthorizedly collect victims' speeches and clone a similar voice for…

声音 · 计算机科学 2025-04-15 Zhisheng Zhang , Derui Wang , Qianyi Yang , Pengyang Huang , Junhan Pu , Yuxin Cao , Kai Ye , Jie Hao , Yixian Yang

Deepfakes are on the rise, with increased sophistication and prevalence allowing for high-profile social engineering attacks. Detecting them in the wild is therefore important as ever, giving rise to new approaches breaking benchmark…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Guy Levy , Nathan Liebmann