相关论文: Listenable Maps for Audio Classifiers

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…

Audio representation learning based on deep neural networks (DNNs) emerged as an alternative approach to hand-crafted features. For achieving high performance, DNNs often need a large amount of annotated data which can be difficult and…

Recently, research on audio foundation models has witnessed notable advances, as illustrated by the ever improving results on complex downstream tasks. Subsequently, those pretrained networks have quickly been used for various audio…

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio…

Machine language acquisition is often presented as a problem of imitation learning: there exists a community of language users from which a learner observes speech acts and attempts to decode the mappings between utterances and situations.…

Despite their success, Large-Language Models (LLMs) still face criticism due to their lack of interpretability. Traditional post-hoc interpretation methods, based on attention and gradient-based analysis, offer limited insights as they only…

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

In predictive modeling for low-resource audio classification, extracting high-accuracy and interpretable attributes is critical. Particularly in high-reliability applications, interpretable audio attributes are indispensable. While…

Multimodal Large Language Models (MLLMs) have been widely applied in speech and music. This tendency has led to a focus on audio tokenization for Large Models (LMs). Unlike semantic-only text tokens, audio tokens must both capture global…

This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tuned for a specific classification task. A classical issue with the fusion of many embeddings…

We address multimodal deepfake detection requiring both robustness and interpretability by proposing FakeHunter, a unified framework that combines memory guided retrieval, a structured Observation-Thought-Action reasoning loop, and adaptive…

Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into…

Lip reading has witnessed unparalleled development in recent years thanks to deep learning and the availability of large-scale datasets. Despite the encouraging results achieved, the performance of lip reading, unfortunately, remains…

The advancements in audio generative models have opened up new challenges in their responsible disclosure and the detection of their misuse. In response, we introduce a method to watermark latent generative models by a specific watermarking…

As one of the most intuitive interfaces known to humans, natural language has the potential to mediate many tasks that involve human-computer interaction, especially in application-focused fields like Music Information Retrieval. In this…

The rapid proliferation of AI-manipulated or generated audio deepfakes poses serious challenges to media integrity and election security. Current AI-driven detection solutions lack explainability and underperform in real-world settings. In…

While sparse autoencoders (SAEs) successfully extract interpretable features from language models, applying them to audio generation faces unique challenges: audio's dense nature requires compression that obscures semantic meaning, and…

Masked image modeling (MIM) has been recognized as a strong self-supervised pre-training approach in the vision domain. However, the mechanism and properties of the learned representations by such a scheme, as well as how to further enhance…

The rapid advancement of generative AI has made it increasingly challenging to distinguish between deepfake audio and authentic human speech. To overcome the limitations of passive detection methods, we propose StreamMark, a novel deep…