相关论文: Scalable Evaluation for Audio Identification via S…

Artificial intelligence and data access are already mainstream. One of the main challenges when designing an artificial intelligence or disclosing content from a database is preserving the privacy of individuals who participate in the…

Real-world deployment of AI vision models is both fueled and limited by the data available for training and testing. Real datasets are sparse and uneven: long-tailed or unbalanced distributions hinder generalization, and the low number of…

Freely available and easy-to-use audio editing tools make it straightforward to perform audio splicing. Convincing forgeries can be created by combining various speech samples from the same person. Detection of such splices is important…

Audio fingerprinting (AFP) allows the identification of unknown audio content by extracting compact representations, termed audio fingerprints, that are designed to remain robust against common audio degradations. Neural AFP methods often…

In this work, we address the challenge of generalizable audio deepfake detection (ADD) across diverse speech synthesis paradigms-including conventional text-to-speech (TTS) systems and modern diffusion or flow-matching (FM) based…

In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…

Audio fingerprinting, exemplified by pioneers like Shazam, has transformed digital audio recognition. However, existing systems struggle with accuracy in challenging conditions, limiting broad applicability. This research proposes an AI and…

AI-synthesized voice technology has the potential to create realistic human voices for beneficial applications, but it can also be misused for malicious purposes. While existing AI-synthesized voice detection models excel in intra-domain…

Assessing the robustness of perception models to covariate shifts and their ability to detect out-of-distribution (OOD) inputs is crucial for safety-critical applications such as autonomous vehicles. By nature of such applications, however,…

The ability to automatically generate music that appropriately matches an arbitrary input track is a challenging task. We present a novel controllable system for generating single stems to accompany musical mixes of arbitrary length. At the…

High-quality datasets for learning-based modelling of polyphonic symbolic music remain less readily-accessible at scale than in other domains, such as language modelling or image classification. Deep learning algorithms show great potential…

Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene Synthesis challenge held as part of the Detection and…

Dialogue state tracking plays a crucial role in extracting information in task-oriented dialogue systems. However, preceding research are limited to textual modalities, primarily due to the shortage of authentic human audio datasets. We…

The ubiquity of sound synthesizers has reshaped music production and even entirely defined new music genres. However, the increasing complexity and number of parameters in modern synthesizers make them harder to master. Hence, the…

In order to achieve good performance and generalisability, medical image segmentation models should be trained on sizeable datasets with sufficient variability. Due to ethics and governance restrictions, and the costs associated with…

We propose an explainable probabilistic framework for characterizing spoofed speech by decomposing it into probabilistic attribute embeddings. Unlike raw high-dimensional countermeasure embeddings, which lack interpretability, the proposed…

The widespread adoption of wearable sensors has the potential to provide massive and heterogeneous time series data, driving the use of Artificial Intelligence in human sensing applications. However, data collection remains limited due to…

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…

Individual-level data (microdata) that characterizes a population, is essential for studying many real-world problems. However, acquiring such data is not straightforward due to cost and privacy constraints, and access is often limited to…

Non-verbal Vocalizations (NVs), such as laughter and sighs, are vital for conveying emotion and intention in human speech, yet most existing speech systems neglect them, which severely compromises communicative richness and emotional…