Related papers: CloneShield: A Framework for Universal Perturbatio…
While recent zero-shot multi-speaker text-to-speech (TTS) models achieve impressive results, they typically rely on extensive transcribed speech datasets from numerous speakers and intricate training pipelines. Meanwhile, self-supervised…
Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy. Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a…
Voice cloning is a prominent feature in personalized speech interfaces. A neural vocal cloning system can mimic someone's voice using just a few audio samples. Both speaker encoding and speaker adaptation are topics of research in the field…
Zero-shot text-to-speech (TTS) has gained significant attention due to its powerful voice cloning capabilities, requiring only a few seconds of unseen speaker voice prompts. However, all previous work has been developed for cloud-based…
Recently, speech assistant and speech verification have been used in many fields, which brings much benefit and convenience for us. However, when we enjoy these speech applications, our speech may be collected by attackers for speech…
Robust speech recognition systems rely on cloud service providers for inference. It needs to ensure that an untrustworthy provider cannot deduce the sensitive content in speech. Sanitization can be done on speech content keeping in mind…
The task of few-shot style transfer for voice cloning in text-to-speech (TTS) synthesis aims at transferring speaking styles of an arbitrary source speaker to a target speaker's voice using very limited amount of neutral data. This is a…
The rapid progress in personalized speech generation technology, including personalized text-to-speech (TTS) and voice conversion (VC), poses a challenge in distinguishing between generated and real speech for human listeners, resulting in…
Most current zero-shot voice conversion methods rely on externally supervised components, particularly speaker encoders, for training. To explore alternatives that eliminate this dependency, this paper introduces GenVC, a novel framework…
Deep learning based voice synthesis technology generates artificial human-like speeches, which has been used in deepfakes or identity theft attacks. Existing defense mechanisms inject subtle adversarial perturbations into the raw speech…
We introduce MiniMax-Speech, an autoregressive Transformer-based Text-to-Speech (TTS) model that generates high-quality speech. A key innovation is our learnable speaker encoder, which extracts timbre features from a reference audio without…
Text embedding inversion attacks reconstruct original sentences from latent representations, posing severe privacy threats in collaborative inference and edge computing. We propose TextCrafter, an optimization-based adversarial perturbation…
Neural Text-to-speech (TTS) synthesis is a powerful technology that can generate speech using neural networks. One of the most remarkable features of TTS synthesis is its capability to produce speech in the voice of different speakers. This…
We introduce OpenVoice, a versatile voice cloning approach that requires only a short audio clip from the reference speaker to replicate their voice and generate speech in multiple languages. OpenVoice represents a significant advancement…
The security of quantum cryptography is guaranteed by the no-cloning theorem, which implies that an eavesdropper copying transmitted qubits in unknown states causes their disturbance. Nevertheless, in real cryptographic systems some level…
Recent developments in large speech foundation models like Whisper have led to their widespread use in many automatic speech recognition (ASR) applications. These systems incorporate `special tokens' in their vocabulary, such as…
Speaker adaptation, which involves cloning voices from unseen speakers in the Text-to-Speech task, has garnered significant interest due to its numerous applications in multi-media fields. Despite recent advancements, existing methods often…
This study explores voice cloning to generate synthetic speech replicating the unique patterns of individuals with dysarthria. Using the TORGO dataset, we address data scarcity and privacy challenges in speech-language pathology. Our…
Occlusion perturbation presents a significant challenge in person re-identification (re-ID), and existing methods that rely on external visual cues require additional computational resources and only consider the issue of missing…
This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery…