Related papers: Breaking Resource Barriers in Speech Emotion Recog…

Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model…

This paper presents an innovative approach to address the challenges of translating multi-modal emotion recognition models to a more practical and resource-efficient uni-modal counterpart, specifically focusing on speech-only emotion…

Speech emotion recognition systems have high prediction latency because of the high computational requirements for deep learning models and low generalizability mainly because of the poor reliability of emotional measurements across…

Significant advances are being made in speech emotion recognition (SER) using deep learning models. Nonetheless, training SER systems remains challenging, requiring both time and costly resources. Like many other machine learning tasks,…

Efficient models for remote sensing object counting are urgently required for applications in scenarios with limited computing resources, such as drones or embedded systems. A straightforward yet powerful technique to achieve this is…

Deep Neural Networks (DNNs) based semantic segmentation of the robotic instruments and tissues can enhance the precision of surgical activities in robot-assisted surgery. However, in biological learning, DNNs cannot learn incremental tasks…

With the rapid scaling of neural networks, data storage and communication demands have intensified. Dataset distillation has emerged as a promising solution, condensing information from extensive datasets into a compact set of synthetic…

Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of…

Self-supervised learned (SSL) speech pre-trained models perform well across various speech processing tasks. Distilled versions of SSL models have been developed to match the needs of on-device speech applications. Though having similar…

The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive…

Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…

Recent years have witnessed great strides in self-supervised learning (SSL) on the speech processing. The SSL model is normally pre-trained on a great variety of unlabelled data and a large model size is preferred to increase the modeling…

Speech emotion recognition aims to identify emotional states from speech signals and has been widely applied in human-computer interaction, education, healthcare, and many other fields. However, since speech data contain rich sensitive…

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…

Speech Emotion Recognition (SER) is essential for improving human-computer interaction, yet its accuracy remains constrained by the complexity of emotional nuances in speech. In this study, we distinguish between descriptive semantics,…

Albeit great performance of Transformer-based speech selfsupervised learning (SSL) models, their large parameter size and computational cost make them unfavorable to utilize. In this study, we propose to compress the speech SSL models by…

Dataset distillation aims to create a small and highly representative synthetic dataset that preserves the essential information of a larger real dataset. Beyond reducing storage and computational costs, related approaches offer a promising…

This paper presents a computationally efficient and distributed speaker diarization framework for networked IoT-style audio devices. The work proposes a Federated Learning model which can identify the participants in a conversation without…

Semantic communications offer the potential to alleviate communication loads by exchanging meaningful information. However, semantic extraction (SE) is computationally intensive, posing challenges for resource-constrained Internet of Things…

The aim of dataset distillation is to encode the rich features of an original dataset into a tiny dataset. It is a promising approach to accelerate neural network training and related studies. Different approaches have been proposed to…