Related papers: CloneShield: A Framework for Universal Perturbatio…

Trusted Execution Environments (TEEs) allow user processes to create enclaves that protect security-sensitive computation against access from the OS kernel and the hypervisor. Recent work has shown that TEEs are vulnerable to side-channel…

Despite rapid progress in text-to-speech (TTS), open-source systems still lack truly instruction-following, fine-grained control over core speech attributes (e.g., pitch, speaking rate, age, emotion, and style). We present VoiceSculptor, an…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…

Recently, studies show that deep learning-based automatic speech recognition (ASR) systems are vulnerable to adversarial examples (AEs), which add a small amount of noise to the original audio examples. These AE attacks pose new challenges…

The few-shot multi-speaker multi-style voice cloning task is to synthesize utterances with voice and speaking style similar to a reference speaker given only a few reference samples. In this work, we investigate different speaker…

In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted…

Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalizability across diverse downstream tasks. However, recent studies have revealed that VLMs, including CLIP, are highly vulnerable to adversarial…

Speech models are often trained on sensitive data in order to improve model performance, leading to potential privacy leakage. Our work considers noise masking attacks, introduced by Amid et al. 2022, which attack automatic speech…

Weakly Supervised Video Anomaly Detection (WSVAD) has achieved notable advancements, yet existing models remain vulnerable to adversarial attacks, limiting their reliability. Due to the inherent constraints of weak supervision, where only…

Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection…

This work proposes FireRedTTS, a foundation text-to-speech framework, to meet the growing demands for personalized and diverse generative speech applications. The framework comprises three parts: data processing, foundation system, and…

Text-based voice editing (TBVE) uses synthetic output from text-to-speech (TTS) systems to replace words in an original recording. Recent work has used neural models to produce edited speech that is similar to the original speech in terms…

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…

Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and…

We introduce VoiceCraft, a token infilling neural codec language model, that achieves state-of-the-art performance on both speech editing and zero-shot text-to-speech (TTS) on audiobooks, internet videos, and podcasts. VoiceCraft employs a…

There are many use cases in singing synthesis where creating voices from small amounts of data is desirable. In text-to-speech there have been several promising results that apply voice cloning techniques to modern deep learning based…

Currently, zero-shot voice conversion systems are capable of synthesizing the voice of unseen speakers. However, most existing approaches struggle to accurately replicate the speaking style of the source speaker or mimic the distinctive…

Previous works have shown that automatic speaker verification (ASV) is seriously vulnerable to malicious spoofing attacks, such as replay, synthetic speech, and recently emerged adversarial attacks. Great efforts have been dedicated to…

We present ChiReSSD, a speech reconstruction framework that preserves children speaker's identity while suppressing mispronunciations. Unlike prior approaches trained on healthy adult speech, ChiReSSD adapts to the voices of children with…

Short-utterance speaker verification presents significant challenges due to the limited information in brief speech segments, which can undermine accuracy and reliability. Recently, zero-shot text-to-speech (ZS-TTS) systems have made…