The study explores the concept of entrainment – the tendency of people to engage in synchronized behavior during interactions. Using Deep Neural Networks (DNN) embeddings like BERT and TRIpLet Loss…
Continue readingThe article presents a new domain adaptation method for speech enhancement, termed as Remixed2Remixed. It uses Noise2Noise learning to adapt models trained on artificially generated noisy-clean pair data to enhance…
Continue readingThe research paper discusses the vulnerability of Deep Neural Networks (DNNs) to adversarial examples. Traditional methods assume that attackers can modify any features, neglecting the causal generating process of data,…
Continue readingThe study focuses on improving the reliability of post-hoc explanation methods in image classification. These methods are used to understand the decision-making processes of deep neural networks, which are often…
Continue readingThe paper explores a scenario where a side-channel attack is used to break the black-box property of embedded artificial intelligence, specifically deep neural networks (DNNs). It presents an architecture-agnostic attack…
Continue readingThe article, ‘Efficient Trigger Word Insertion’, focuses on the threats posed by backdoor attacks on deep neural network models in the field of Natural Language Processing (NLP). The authors propose…
Continue readingThe authors introduce the Temporal Audio Source Counting Network (TaCNet), a new architecture that addresses issues in audio source counting tasks. TaCNet works directly on raw audio inputs, removing the…
Continue readingThe article explores the role of deep neural networks (DNNs) in automatic speaker recognition, particularly in modeling supra-segmental temporal information (SST). Despite their success, the understanding of what contributes to…
Continue readingThe study presents a novel test to measure how much the performance of neural networks in speaker recognition can be attributed to the modeling of supra-segmental temporal features (SST). It…
Continue readingThe paper introduces a certified backdoor detector (CBD) for deep neural networks. The CBD is based on a conformal prediction scheme and uses a statistic called local dominant probability. The…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
