Related papers: FairSSD: Understanding Bias in Synthetic Speech De…

Distinguishing scripted from spontaneous speech is an essential tool for better understanding how speech styles influence speech processing research. It can also improve recommendation systems and discovery experiences for media users…

Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of…

Speech production is a complex phenomenon, wherein the brain orchestrates a sequence of processes involving thought processing, motor planning, and the execution of articulatory movements. However, this intricate execution of various…

Research on non-verbal behavior generation for social interactive agents focuses mainly on the believability and synchronization of non-verbal cues with speech. However, existing models, predominantly based on deep learning architectures,…

This paper presents novel experiments shedding light on the shortcomings of current metrics for assessing biases of gender discrimination made by machine learning algorithms on textual data. We focus on the Bios dataset, and our learning…

This paper addresses the challenge of speaker separation, which remains an active research topic despite the promising results achieved in recent years. These results, however, often degrade in real recording conditions due to the presence…

The modern generative audio models can be used by an adversary in an unlawful manner, specifically, to impersonate other people to gain access to private information. To mitigate this issue, speech deepfake detection (SDD) methods started…

Modern sequence to sequence neural TTS systems provide close to natural speech quality. Such systems usually comprise a network converting linguistic/phonetic features sequence to an acoustic features sequence, cascaded with a neural…

Speech deepfake detection has achieved remarkable success in clean environments but faces significant challenges in complex, real-world scenarios where speech is often mixed with background music or noise. Current state-of-the-art methods…

The mapping of text to speech (TTS) is non-deterministic, letters may be pronounced differently based on context, or phonemes can vary depending on various physiological and stylistic factors like gender, age, accent, emotions, etc. Neural…

With the rapid development of deep learning techniques, the generation and counterfeiting of multimedia material are becoming increasingly straightforward to perform. At the same time, sharing fake content on the web has become so simple…

The rapid advances in text-to-speech (TTS) technologies have made audio deepfakes increasingly realistic and accessible, raising significant security and trust concerns. While existing research has largely focused on detecting…

The evaluation of audio fingerprinting at a realistic scale is limited by the scarcity of large public music databases. We present an audio-free approach that synthesises latent fingerprints which approximate the distribution of real…

Speaker identity plays a significant role in human communication and is being increasingly used in societal applications, many through advances in machine learning. Speaker identity perception is an essential cognitive phenomenon that can…

Researchers have devised numerous ways to quantify social biases vested in pretrained language models. As some language models are capable of generating coherent completions given a set of textual prompts, several prompting datasets have…

The rapid advancement of generative models has enabled the creation of increasingly stealthy synthetic voices, commonly referred to as audio deepfakes. A recent technique, FOICE [USENIX'24], demonstrates a particularly alarming capability:…

Despite the success of deep neural networks (DNNs) in enabling on-device voice assistants, increasing evidence of bias and discrimination in machine learning is raising the urgency of investigating the fairness of these systems. Speaker…

The rise of deepfake audio and hate speech, powered by advanced text-to-speech, threatens online safety. We present SynHate, the first multilingual dataset for detecting hate speech in synthetic audio, spanning 37 languages. SynHate uses a…

Synthetic data has emerged as a promising alternative for training face recognition (FR) models, offering advantages in scalability, privacy compliance, and potential for bias mitigation. However, critical questions remain on whether both…

Recent techniques for speech deepfake detection often rely on pre-trained self-supervised models. These systems, initially developed for Automatic Speech Recognition (ASR), have proved their ability to offer a meaningful representation of…