Related papers: DarkStream: real-time speech anonymization with lo…
In this work, we propose a novel method for modeling numerous speakers, which enables expressing the overall characteristics of speakers in detail like a trained multi-speaker model without additional training on the target speaker's…
Streaming speech-to-avatar synthesis creates real-time animations for a virtual character from audio data. Accurate avatar representations of speech are important for the visualization of sound in linguistics, phonetics, and phonology,…
Human speech conveys prosody, linguistic content, and speaker identity. This article investigates a novel speaker anonymization approach using an end-to-end network based on a Vector-Quantized Variational Auto-Encoder (VQ-VAE) to deal with…
Automatic speaker recognition algorithms typically characterize speech audio using short-term spectral features that encode the physiological and anatomical aspects of speech production. Such algorithms do not fully capitalize on…
Speech Enhancement techniques have become core technologies in mobile devices and voice software. Still, modern deep learning solutions often require high amount of computational resources what makes their usage on low-resource devices…
Real-time speech synthesis requires balancing inference latency and acoustic fidelity for interactive applications. Conventional continuous text-to-speech pipelines require computationally intensive neural vocoders to reconstruct phase…
Voice anonymization protects speaker privacy by concealing identity while preserving linguistic and paralinguistic content. Self-supervised learning (SSL) representations encode linguistic features but preserve speaker traits. We propose a…
This work proposes a frame-wise online/streaming end-to-end neural diarization (EEND) method, which detects speaker activities in a frame-in-frame-out fashion. The proposed model mainly consists of a causal embedding encoder and an online…
Anonymization of voice seeks to conceal the identity of the speaker while maintaining the utility of speech data. However, residual speaker cues often persist, which pose privacy risks. We propose SegReConcat, a data augmentation method for…
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…
Text-to-Speech (TTS) and Voice Conversion (VC) models have exhibited remarkable performance in generating realistic and natural audio. However, their dark side, audio deepfake poses a significant threat to both society and individuals.…
Speaker anonymization aims to conceal a speaker's identity, without considering the linguistic content. In this study, we reveal a weakness of Librispeech, the dataset that is commonly used to evaluate anonymizers: the books read by the…
We introduce a sophisticated multi-speaker speech data simulator, specifically engineered to generate multi-speaker speech recordings. A notable feature of this simulator is its capacity to modulate the distribution of silence and overlap…
The presence of multiple talkers in the surrounding environment poses a difficult challenge for real-time speech communication systems considering the constraints on network size and complexity. In this paper, we present Personalized…
Environmental sound recordings often contain intelligible speech, raising privacy concerns that limit analysis, sharing and reuse of data. In this paper, we introduce a method that renders speech unintelligible while preserving both the…
The widespread adoption of speech-based online services raises security and privacy concerns regarding the data that they use and share. If the data were compromised, attackers could exploit user speech to bypass speaker verification…
Voice data generated on instant messaging or social media applications contains unique user voiceprints that may be abused by malicious adversaries for identity inference or identity theft. Existing voice anonymization techniques, e.g.,…
Generating high-quality speech efficiently remains a key challenge for generative models in speech synthesis. This paper introduces VQalAttent, a lightweight model designed to generate fake speech with tunable performance and…
WaveCycleGAN has recently been proposed to bridge the gap between natural and synthesized speech waveforms in statistical parametric speech synthesis and provides fast inference with a moving average model rather than an autoregressive…
In this paper, we propose a multi-speaker face-to-speech waveform generation model that also works for unseen speaker conditions. Using a generative adversarial network (GAN) with linguistic and speaker characteristic features as auxiliary…