相关论文: SCDF: A Speaker Characteristics DeepFake Speech Da…

Speaker embeddings are widely used in speaker verification systems and other applications where it is useful to characterise the voice of a speaker with a fixed-length vector. These embeddings tend to be treated as "black box" encodings,…

With the huge technological advances introduced by deep learning in audio & speech processing, many novel synthetic speech techniques achieved incredible realistic results. As these methods generate realistic fake human voices, they can be…

The conversation scenario is one of the most important and most challenging scenarios for speech processing technologies because people in conversation respond to each other in a casual style. Detecting the speech activities of each person…

A large and growing amount of speech content in real-life scenarios is being recorded on consumer-grade devices in uncontrolled environments, resulting in degraded speech quality. Transforming such low-quality device-degraded speech into…

Recently, attention mechanisms have been applied successfully in neural network-based speaker verification systems. Incorporating the Squeeze-and-Excitation block into convolutional neural networks has achieved remarkable performance.…

Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities. However, these models often inherit deep-rooted social biases from their training…

The Automatic Speaker Verification (ASV) system is vulnerable to fraudulent activities using audio deepfakes, also known as logical-access voice spoofing attacks. These deepfakes pose a concerning threat to voice biometrics due to recent…

Automatic speaker verification (ASV) systems utilize the biometric information in human speech to verify the speaker's identity. The techniques used for performing speaker verification are often vulnerable to malicious attacks that attempt…

Enhancing explainability in speech self-supervised learning (SSL) is important for developing reliable SSL-based speech processing systems. This study probes how speech SSL models encode speaker-specific information via a large-scale…

Deepfakes have become a universal and rapidly intensifying concern of generative AI across various media types such as images, audio, and videos. Among these, audio deepfakes have been of particular concern due to the ease of high-quality…

Current automatic speech recognition (ASR) models are designed to be used across many languages and tasks without substantial changes. However, this broad language coverage hides performance gaps within languages, for example, across…

Generative spoken language models produce speech in a wide range of voices, prosody, and recording conditions, seemingly approaching the diversity of natural speech. However, the extent to which generated speech is acoustically diverse…

Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…

Speaker verification systems are vulnerable to spoofing attacks which presents a major problem in their real-life deployment. To date, most of the proposed synthetic speech detectors (SSDs) have weighted the importance of different segments…

Detecting synthetic from real speech is increasingly crucial due to the risks of misinformation and identity impersonation. While various datasets for synthetic speech analysis have been developed, they often focus on specific areas,…

Aphasia is a language disorder that affects the speaking ability of millions of patients. This paper presents a new benchmark for Aphasia speech recognition and detection tasks using state-of-the-art speech recognition techniques with the…

While language identification is a fundamental speech and language processing task, for many languages and language families it remains a challenging task. For many low-resource and endangered languages this is in part due to resource…

Audio-based depression detection models have demonstrated promising performance but often suffer from gender bias due to imbalanced training data. Epidemiological statistics show a higher prevalence of depression in females, leading models…

With the ubiquity of smart devices that use speaker recognition (SR) systems as a means of authenticating individuals and personalizing their services, fairness of SR systems has becomes an important point of focus. In this paper we study…

Synthesized speech is common today due to the prevalence of virtual assistants, easy-to-use tools for generating and modifying speech signals, and remote work practices. Synthesized speech can also be used for nefarious purposes, including…