Related papers: Curriculum Learning for Speech Emotion Recognition…

Emotion recognition from speech is a challenging task. Re-cent advances in deep learning have led bi-directional recur-rent neural network (Bi-RNN) and attention mechanism as astandard method for speech emotion recognition, extractingand…

Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy…

Some of the most severe bottlenecks preventing widespread development of machine learning models for human behavior include a dearth of labeled training data and difficulty of acquiring high quality labels. Active learning is a paradigm for…

Emotions widely affect human decision-making. This fact is taken into account by affective computing with the goal of tailoring decision support to the emotional states of individuals. However, the accurate recognition of emotions within…

Neural networks are one of the most popular approaches for many natural language processing tasks such as sentiment analysis. They often outperform traditional machine learning models and achieve the state-of-art results on most tasks.…

The main task of Multimodal Emotion Recognition in Conversations (MERC) is to identify the emotions in modalities, e.g., text, audio, image and video, which is a significant development direction for realizing machine intelligence. However,…

Labeling real-world datasets is time consuming but indispensable for supervised machine learning models. A common solution is to distribute the labeling task across a large number of non-expert workers via crowd-sourcing. Due to the varying…

The social networking sites have brought a new horizon for expressing views and opinions of individuals. Moreover, they provide medium to students to share their sentiments including struggles and joy during the learning process. Such…

In the field of machine learning, the well-trained model is assumed to be able to recover the training labels, i.e. the synthetic labels predicted by the model should be as close to the ground-truth labels as possible. Inspired by this, we…

The goal of this paper is to train effective self-supervised speaker representations without identity labels. We propose two curriculum learning strategies within a self-supervised learning framework. The first strategy aims to gradually…

Speech emotion recognition (SER) systems find applications in various fields such as healthcare, education, and security and defense. A major drawback of these systems is their lack of generalization across different conditions. This…

Density regression has been widely employed in crowd counting. However, the frequency imbalance of pixel values in the density map is still an obstacle to improve the performance. In this paper, we propose a novel learning strategy for…

Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much…

Curriculum learning (CL) - ordering training data from easy to hard - has become a popular strategy for improving reasoning in large language models (LLMs). Yet prior work employs disparate difficulty metrics and training setups, leaving…

Automated emotion recognition in speech is a long-standing problem. While early work on emotion recognition relied on hand-crafted features and simple classifiers, the field has now embraced end-to-end feature learning and classification…

Curriculum learning is a bio-inspired training technique that is widely adopted to machine learning for improved optimization and better training of neural networks regarding the convergence rate or obtained accuracy. The main concept in…

Word embeddings have been widely used in sentiment classification because of their efficacy for semantic representations of words. Given reviews from different domains, some existing methods for word embeddings exploit sentiment…

Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While both methods…

Selecting an effective training signal for machine learning tasks is difficult: expert annotations are expensive, and crowd-sourced annotations may not be reliable. Recent work has demonstrated that learning from a distribution over labels…

Recently the deep learning techniques have achieved success in multi-label classification due to its automatic representation learning ability and the end-to-end learning framework. Existing deep neural networks in multi-label…