相关论文: Hybrid Audio Detection Using Fine-Tuned Audio Spec…
The audio segmentation mismatch between training data and those seen at run-time is a major problem in direct speech translation. Indeed, while systems are usually trained on manually segmented corpora, in real use cases they are often…
Audio deepfakes pose a growing threat, already exploited in fraud and misinformation. A key challenge is ensuring detectors remain robust to unseen synthesis methods and diverse speakers, since generation techniques evolve quickly. Despite…
With the rapid development of artificial intelligence (AI), digital humans have attracted more and more attention and are expected to achieve a wide range of applications in several industries. Then, most of the existing digital humans…
Audio deepfake detection is an emerging topic in the artificial intelligence community. The second Audio Deepfake Detection Challenge (ADD 2023) aims to spur researchers around the world to build new innovative technologies that can further…
Autism Spectrum Disorder (ASD) is a complex neuro-developmental challenge, presenting a spectrum of difficulties in social interaction, communication, and the expression of repetitive behaviors in different situations. This increasing…
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,…
Large Language Models and commercial speech synthesis systems now enable highly realistic AI-generated voice scams (vishing), raising urgent concerns about deception at scale. Yet it remains unclear whether individuals can reliably…
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…
This thesis addresses the technical challenges of applying machine learning to understand and interpret medical audio signals. The sounds of our lungs, heart, and voice convey vital information about our health. Yet, in contemporary…
Recently, the AI community has made significant strides in developing powerful foundation models, driven by large-scale multimodal datasets. However, for audio representation learning, existing datasets suffer from limitations in the…
Recognizing human non-speech vocalizations is an important task and has broad applications such as automatic sound transcription and health condition monitoring. However, existing datasets have a relatively small number of vocal sound…
Unmanned aerial vehicles (UAVs), commonly known as drones, are increasingly used across diverse domains, including logistics, agriculture, surveillance, and defense. While these systems provide numerous benefits, their misuse raises safety…
Automatic speaker verification (ASV) technology is recently finding its way to end-user applications for secure access to personal data, smart services or physical facilities. Similar to other biometric technologies, speaker verification is…
As Artificial Intelligence (AI) technologies continue to evolve, their use in generating realistic, contextually appropriate content has expanded into various domains. Music, an art form and medium for entertainment, deeply rooted into…
Machine Listening, as usually formalized, attempts to perform a task that is, from our perspective, fundamentally human-performable, and performed by humans. Current automated models of Machine Listening vary from purely data-driven…
The state-of-art models for speech synthesis and voice conversion are capable of generating synthetic speech that is perceptually indistinguishable from bonafide human speech. These methods represent a threat to the automatic speaker…
Hearing aids (HAs) are widely used to provide personalized speech enhancement (PSE) services, improving the quality of life for individuals with hearing loss. However, HA performance significantly declines in noisy environments as it treats…
Speaker verification is to judge the similarity between two unknown voices in an open set, where the ideal speaker embedding should be able to condense discriminant information into a compact utterance-level representation that has small…
In the past, Acoustic Scene Classification systems have been based on hand crafting audio features that are input to a classifier. Nowadays, the common trend is to adopt data driven techniques, e.g., deep learning, where audio…
Audio impairment recognition is based on finding noise in audio files and categorising the impairment type. Recently, significant performance improvement has been obtained thanks to the usage of advanced deep learning models. However,…