中文
相关论文

相关论文: MelShield: Robust Mel-Domain Audio Watermarking fo…

200 篇论文

We introduce TextSeal, a state-of-the-art watermark for large language models. Building on Gumbel-max sampling, TextSeal introduces dual-key generation to restore output diversity, along with entropy-weighted scoring and multi-region…

The task of Mel vocoding, i.e., the inversion of a Mel magnitude spectrogram to an audio waveform, is still a key component in many text-to-speech (TTS) systems today. Based on generative flow matching, our prior work on generative STFT…

音频与语音处理 · 电气工程与系统科学 2025-09-19 Simon Welker , Tal Peer , Timo Gerkmann

Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, demonstrating human-level performance in text generation, reasoning, and question answering. However, training such…

密码学与安全 · 计算机科学 2025-11-17 Yanbo Dai , Zongjie Li , Zhenlan Ji , Shuai Wang

We present CallShield, the first caller identity authentication system that operates entirely at the audio layer, without relying on speech transcription, internet connectivity, or trusted infrastructure. CallShield introduces a real-time…

密码学与安全 · 计算机科学 2026-01-15 Mouna Rabh , Yazan Boshmaf , Mashael Alsabah , Shammur Chowdhury , Mohamed Hefeeda , Issa Khalil

The rapid proliferation of generative audio synthesis and editing technologies has raised serious concerns about copyright infringement, data provenance, and the spread of misinformation via deepfake audio. Watermarking offers a proactive…

声音 · 计算机科学 2026-05-25 Yixin Liu , Lie Lu , Jihui Jin , Lichao Sun , Andrea Fanelli

Diffusion models have gained prominence in the image domain for their capabilities in data generation and transformation, achieving state-of-the-art performance in various tasks in both image and audio domains. In the rapidly evolving field…

声音 · 计算机科学 2023-11-02 Xirong Cao , Xiang Li , Divyesh Jadav , Yanzhao Wu , Zhehui Chen , Chen Zeng , Wenqi Wei

In the rapidly evolving field of speech generative models, there is a pressing need to ensure audio authenticity against the risks of voice cloning. We present AudioSeal, the first audio watermarking technique designed specifically for…

Generative models have rapidly evolved to generate realistic outputs. However, their synthetic outputs increasingly challenge the clear distinction between natural and AI-generated content, necessitating robust watermarking techniques.…

机器学习 · 计算机科学 2026-05-20 Kasra Arabi , R. Teal Witter , Chinmay Hegde , Niv Cohen

As artificial intelligence surpasses human capabilities in text generation, the necessity to authenticate the origins of AI-generated content has become paramount. Unbiased watermarks offer a powerful solution by embedding statistical…

计算与语言 · 计算机科学 2025-08-07 Ruibo Chen , Yihan Wu , Junfeng Guo , Heng Huang

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated…

计算与语言 · 计算机科学 2026-05-29 Yukang Lin , Jiahao Shao , Shuoran Jiang , Wentao Zhu , Bingjie Lu , Xiangping Wu , Joanna Siebert , Qingcai Chen

Voice interfaces are quickly becoming a common way for people to interact with AI systems. This also brings new security risks, such as prompt injection, social engineering, and harmful voice commands. Traditional security methods rely on…

声音 · 计算机科学 2026-03-10 Sumit Ranjan , Sugandha Sharma , Ubaid Abbas , Puneeth N Ail

The indistinguishability of large language model (LLM) output from human-authored content poses significant challenges, raising concerns about potential misuse of AI-generated text and its influence on future model training. Watermarking…

密码学与安全 · 计算机科学 2026-04-16 Alexander Nemecek , Yuzhou Jiang , Erman Ayday

The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a promising solution: model owners can embed an imperceptible…

密码学与安全 · 计算机科学 2025-11-04 Shingo Kodama , Haya Diwan , Lucas Rosenblatt , R. Teal Witter , Niv Cohen

Self-supervised learning is an emerging machine learning paradigm. Compared to supervised learning which leverages high-quality labeled datasets, self-supervised learning relies on unlabeled datasets to pre-train powerful encoders which can…

密码学与安全 · 计算机科学 2022-09-02 Tianshuo Cong , Xinlei He , Yang Zhang

Speech provenance goes beyond detecting whether a watermark is present. Real workflows involve splicing, quoting, trimming, and platform-level transforms that may preserve some regions while altering others. Neural watermarking systems have…

密码学与安全 · 计算机科学 2026-02-12 Tatsunori Ono

The rapid advancement of generative AI has made it increasingly challenging to distinguish between deepfake audio and authentic human speech. To overcome the limitations of passive detection methods, we propose StreamMark, a novel deep…

音频与语音处理 · 电气工程与系统科学 2026-04-15 Zhentao Liu , Milos Cernak

Recent breakthroughs in zero-shot voice synthesis have enabled imitating a speaker's voice using just a few seconds of recording while maintaining a high level of realism. Alongside its potential benefits, this powerful technology…

声音 · 计算机科学 2024-01-09 Guangyu Chen , Yu Wu , Shujie Liu , Tao Liu , Xiaoyong Du , Furu Wei

Generative AI models pose a significant challenge to intellectual property (IP), as they can replicate unique artistic styles and concepts without attribution. While watermarking offers a potential solution, existing methods often fail in…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Li Zhang , Shruti Agarwal , John Collomosse , Pengtao Xie , Vishal Asnani

Large language models are now embedded in everyday writing workflows, making reliable AI-generated text detection important for academic integrity, content moderation, and provenance tracking. In practice, however, a detector must do more…

计算与语言 · 计算机科学 2026-05-11 Chenjun Li , Cheng Wan , Johannes C. Paetzold

Ultra-low-bitrate speech coding is pivotal for bandwidth-constrained communication and deep compression, yet maintaining naturalness and speaker identity at such extreme bit budgets remains challenging due to pronounced information loss and…

音频与语音处理 · 电气工程与系统科学 2026-05-26 Hui-Peng Du , Yang Ai , Xiao-Hang Jiang , Yuan Tian , Zhen-Hua Ling
‹ 上一页 1 2 3 10 下一页 ›