Related papers: Yeah, Right, Uh-Huh: A Deep Learning Backchannel P…

Automatic deepfake detection has received considerable research attention, yet the socio-technical environment in which humans actually encounter synthetic speech remains poorly understood. We investigate voice deepfake detection as a…

Interest in biologically inspired alternatives to backpropagation is driven by the desire to both advance connections between deep learning and neuroscience and address backpropagation's shortcomings on tasks such as online, continual…

We propose a novel deep neural network architecture for speech recognition that explicitly employs knowledge of the background environmental noise within a deep neural network acoustic model. A deep neural network is used to predict the…

The task of person re-identification has recently received rising attention due to the high performance achieved by new methods based on deep learning. In particular, in the context of video-based re-identification, many state-of-the-art…

Deep learning has emerged as a powerful alternative to hand-crafted methods for emotion recognition on combined acoustic and text modalities. Baseline systems model emotion information in text and acoustic modes independently using Deep…

Using neural networks to generate replies in human-computer dialogue systems is attracting increasing attention over the past few years. However, the performance is not satisfactory: the neural network tends to generate safe, universally…

Emotion recognition in social situations is a complex task that requires integrating information from both facial expressions and the situational context. While traditional approaches to automatic emotion recognition have focused on…

We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if…

User interactions with personal assistants like Alexa, Google Home and Siri are typically initiated by a wake term or wakeword. Several personal assistants feature "follow-up" modes that allow users to make additional interactions without…

The notion of a Brain-Computer Interface system is the acquisition of signals from the brain, processing them, and translating them into commands. The study concentrated on a specific sort of brain signal known as Motor Imagery EEG signals,…

Deep reinforcement learning (deep RL) is a combination of deep learning with reinforcement learning principles to create efficient methods that can learn by interacting with its environment. This has led to breakthroughs in many complex…

Large language models (LLMs) often exhibit strong biases, e.g, against women or in favor of the number 7. We investigate whether LLMs would be able to output less biased answers when allowed to observe their prior answers to the same…

Brain-computer interfaces (BCIs) use brain signals such as electroencephalography to reflect user intention and enable two-way communication between computers and users. BCI technology has recently received much attention in healthcare…

Replacing hand-engineered pipelines with end-to-end deep learning systems has enabled strong results in applications like speech and object recognition. However, the causality and latency constraints of production systems put end-to-end…

This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neural network, capable of…

End-to-end learning of a communications system using the deep learning-based autoencoder concept has drawn interest in recent research due to its simplicity, flexibility and its potential of adapting to complex channel models and practical…

Studies of human decision-making demonstrate that environmental regularities, such as natural image statistics or intentionally nonuniform stimulus probabilities, can be exploited to improve efficiency (termed `efficient-coding').…

Speech-related Brain Computer Interface (BCI) technologies provide effective vocal communication strategies for controlling devices through speech commands interpreted from brain signals. In order to infer imagined speech from active…

Artificial intelligence (AI) systems can detect disease-related acoustic patterns in cough sounds, offering a scalable and cost-effective approach to tuberculosis (TB) screening in high-burden, resource-limited settings. Previous studies…

As prior knowledge of objects or object features helps us make relations for similar objects on attentional tasks, pre-trained deep convolutional neural networks (CNNs) can be used to detect salient objects on images regardless of the…