Related papers: Best Practices for Noise-Based Augmentation to Imp…

Uncertainty in machine learning models is a timely and vast field of research. In supervised learning, uncertainty can already occur in the first stage of the training process, the annotation phase. This scenario is particularly evident…

Multimodal Sentiment Analysis (MSA) integrates complementary features from text, video, and audio for robust emotion understanding in human interactions. However, models suffer from severe data scarcity and high annotation costs, severely…

In recent years, research on learning with noisy labels has focused on devising novel algorithms that can achieve robustness to noisy training labels while generalizing to clean data. These algorithms often incorporate sophisticated…

In attempts to produce ML models less reliant on spurious patterns in NLP datasets, researchers have recently proposed curating counterfactually augmented data (CAD) via a human-in-the-loop process in which given some documents and their…

In the presence of noisy or incorrect labels, neural networks have the undesirable tendency to memorize information about the noise. Standard regularization techniques such as dropout, weight decay or data augmentation sometimes help, but…

Labelling of data for supervised learning can be costly and time-consuming and the risk of incorporating label noise in large data sets is imminent. When training a flexible discriminative model using a strictly proper loss, such noise will…

In speech emotion recognition (SER), using predefined features without considering their practical importance may lead to high dimensional datasets, including redundant and irrelevant information. Consequently, high-dimensional learning…

Recent advances in reinforcement learning (RL) have strengthened the reasoning capabilities of vision-language models (VLMs). However, enhancing policy exploration to better scale test-time compute remains largely underexplored. In…

We introduce ImportantAug, a technique to augment training data for speech classification and recognition models by adding noise to unimportant regions of the speech and not to important regions. Importance is predicted for each utterance…

Researchers have raised awareness about the harms of aggregating labels especially in subjective tasks that naturally contain disagreements among human annotators. In this work we show that models that are only provided aggregated labels…

End-to-end models have achieved significant improvement on automatic speech recognition. One common method to improve performance of these models is expanding the data-space through data augmentation. Meanwhile, human auditory inspired…

Although the terms mood and emotion are closely related and often used interchangeably, they are distinguished based on their duration, intensity and attribution. To date, hardly any computational models have (a) examined mood recognition,…

Despite the widespread utilization of deep neural networks (DNNs) for speech emotion recognition (SER), they are severely restricted due to the paucity of labeled data for training. Recently, segment-based approaches for SER have been…

Noisy labels are ubiquitous in real-world datasets, especially in the large-scale ones derived from crowdsourcing and web searching. It is challenging to train deep neural networks with noisy datasets since the networks are prone to…

Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy speech from the…

Emotion recognition in text, the task of identifying emotions such as joy or anger, is a challenging problem in NLP with many applications. One of the challenges is the shortage of available datasets that have been annotated with emotions.…

Affective computing is a field of study that focuses on developing systems and technologies that can understand, interpret, and respond to human emotions. Speech Emotion Recognition (SER), in particular, has got a lot of attention from…

Current language model memory systems store what happened but not how it felt. This distinction -- between semantic memory (knowing about a past event) and episodic memory (re-experiencing it) -- was identified by Tulving as the difference…

Noisy labels can impair model performance, making the study of learning with noisy labels an important topic. Two conventional approaches are noise modeling and noise detection. However, these two methods are typically studied…

Stochastic resonance is a non-linear phenomenon, in which the sensitivity of signal detectors can be enhanced by adding random noise to the detector input. Here, we demonstrate that noise can also improve the information flux in recurrent…