Related papers: Formal Verification of Long Short-Term Memory base…
Audio-based equipment condition monitoring suffers from a lack of standardized methodologies for algorithm selection, hindering reproducible research. This paper addresses this gap by introducing a comprehensive framework for the systematic…
Audiovisual scenes are pervasive in our daily life. It is commonplace for humans to discriminatively localize different sounding objects but quite challenging for machines to achieve class-aware sounding objects localization without…
The ability to localize and track acoustic events is a fundamental prerequisite for equipping machines with the ability to be aware of and engage with humans in their surrounding environment. However, in realistic scenarios, audio signals…
Verifying if two audio segments belong to the same speaker has been recently put forward as a flexible way to carry out speaker identification, since it does not require to be re-trained when new speakers appear on the auditory scene.…
Formal verification techniques play a pivotal role in ensuring the safety of complex cyber-physical systems. To transfer model-based verification results to the real world, we require that the measurements of the target system lie in the…
The rapid development of audio-driven talking head generators and advanced Text-To-Speech (TTS) models has led to more sophisticated temporal deepfakes. These advances highlight the need for robust methods capable of detecting and…
While efficient architectures and a plethora of augmentations for end-to-end image classification tasks have been suggested and heavily investigated, state-of-the-art techniques for audio classifications still rely on numerous…
This work presents a novel framework based on feed-forward neural network for text-independent speaker classification and verification, two related systems of speaker recognition. With optimized features and model training, it achieves 100%…
In this paper we present a data-driven, integrated approach to speaker verification, which maps a test utterance and a few reference utterances directly to a single score for verification and jointly optimizes the system's components using…
Aligning large language models (LLMs) with human values is crucial for safe deployment. Inference-time techniques offer granular control over generation; however, they rely on model uncertainty, meaning an internal estimate of how likely…
Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Speaker Recognition Evaluation) datasets. From the practical…
Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine learning-based classifiers are commonly employed to detect…
With ever-increasing number of car-mounted electric devices and their complexity, audio classification is increasingly important for the automotive industry as a fundamental tool for human-device interactions. Existing approaches for audio…
Most audio tagging models are trained with one-hot labels as supervised information. However, one-hot labels treat all sound events equally, ignoring the semantic hierarchy and proximity relationships between sound events. In contrast, the…
Audio tagging is the task of predicting the presence or absence of sound classes within an audio clip. Previous work in audio tagging focused on relatively small datasets limited to recognising a small number of sound classes. We…
Speech intelligibility can be degraded due to multiple factors, such as noisy environments, technical difficulties or biological conditions. This work is focused on the development of an automatic non-intrusive system for predicting the…
With the proliferation of speech deepfake generators, it becomes crucial not only to assess the authenticity of synthetic audio but also to trace its origin. While source attribution models attempt to address this challenge, they often…
Humans are able to localize objects in the environment using both visual and auditory cues, integrating information from multiple modalities into a common reference frame. We introduce a system that can leverage unlabeled audio-visual data…
Sound event localization frameworks based on deep neural networks have shown increased robustness with respect to reverberation and noise in comparison to classical parametric approaches. In particular, recurrent architectures that…
Continuously learning a variety of audio-video semantics over time is crucial for audio-related reasoning tasks in our ever-evolving world. However, this is a nontrivial problem and poses two critical challenges: sparse spatio-temporal…