Search Results for author:
Found 23 papers, 4 papers with code
A Lightweight Attention-based Deep Network via Multi-Scale Feature Fusion for Multi-View Facial Expression Recognition
On the other hand, the PWFS block employs a feature selection mechanism that discards less meaningful features prior to the fusion process.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition
This study presents emoDARTS, a DARTS-optimised joint CNN and Sequential Neural Network (SeqNN: LSTM, RNN) architecture that enhances SER performance.
Ranked #1 on
Speech Emotion Recognition
on MSP-IMPROV
Integrating Contrastive Learning into a Multitask Transformer Model for Effective Domain Adaptation
While speech emotion recognition (SER) research has made significant progress, achieving generalization across various corpora continues to pose a problem.
Natural Language Processing in Electronic Health Records in Relation to Healthcare Decision-making: A Systematic Review
Various Machine Learning (ML), Deep Learning (DL) and NLP techniques are studied and compared to understand the limitations and opportunities in this space comprehensively.
Enhancing Speech Emotion Recognition Through Differentiable Architecture Search
In contrast to previous studies, we refrain from imposing constraints on the order of the layers for the CNN within the DARTS cell; instead, we allow DARTS to determine the optimal layer order autonomously.
Ranked #5 on
Speech Emotion Recognition
on IEMOCAP
(UA metric)
Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering
We propose \textit{RAG-end2end}, an extension to RAG, that can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training.
Speech Synthesis with Mixed Emotions
We then incorporate our formulation into a sequence-to-sequence emotional text-to-speech framework.
Domain Adapting Deep Reinforcement Learning for Real-world Speech Emotion Recognition
Evaluation results show that in a live data feed setting, RL-DA outperforms a baseline strategy by 11% and 14% in cross-corpus and cross-language scenarios, respectively.
Emotion Intensity and its Control for Emotional Voice Conversion
As desired, the proposed network controls the fine-grained emotion intensity in the output speech.
A novel policy for pre-trained Deep Reinforcement Learning for Speech Emotion Recognition
In addition, extended learning period is a general challenge for deep RL which can impact the speed of learning for SER.
High-Fidelity Audio Generation and Representation Learning with Guided Adversarial Autoencoder
Hence, with the extensive experimental results, we have demonstrated that by harnessing the power of the high-fidelity audio generation, the proposed GAAE model can learn powerful representation from unlabelled dataset leveraging a fewer percentage of labelled data as supervision/guidance.
Guided Generative Adversarial Neural Network for Representation Learning and High Fidelity Audio Generation using Fewer Labelled Audio Data
However, the model can become redundant if it is intended for a specific task.
Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends
Research on speech processing has traditionally considered the task of designing hand-engineered acoustic features (feature engineering) as a separate distinct problem from the task of designing efficient machine learning (ML) models to make prediction and classification decisions.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Pre-training in Deep Reinforcement Learning for Automatic Speech Recognition
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Disentangled Representation Learning with Information Maximizing Autoencoder
Learning disentangled representation from any unlabelled data is a non-trivial problem.
Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustness
Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems.
Automating Motion Correction in Multishot MRI Using Generative Adversarial Networks
Multishot Magnetic Resonance Imaging (MRI) has recently gained popularity as it accelerates the MRI data acquisition process without compromising the quality of final MR image.
Phonocardiographic Sensing using Deep Learning for Abnormal Heartbeat Detection
Our choice of RNNs is motivated by the great success of deep learning in medical applications and by the observation that RNNs represent the deep learning configuration most suitable for dealing with sequential or temporal data even in the presence of noise.
Transfer Learning for Improving Speech Emotion Classification Accuracy
The majority of existing speech emotion recognition research focuses on automatic emotion detection using training and testing data from same corpus collected under the same conditions.
Image denoising and restoration with CNN-LSTM Encoder Decoder with Direct Attention
In the proposed model, the encoder reads an image and catches the abstraction of that image in a vector, where decoder takes that vector as well as the corrupted image to reconstruct a clean image.
Variational Autoencoders for Learning Latent Representations of Speech Emotion: A Preliminary Study
Inspired by this, we propose VAEs for deriving the latent representation of speech signals and use this representation to classify emotions.
Sparse Bayesian Learning for EEG Source Localization
Methods: To better specify the sparsity profile and to ensure efficient source localization, the proposed approach considers grouping of the electrical current dipoles inside human brain.
Novel Methods for Activity Classification and Occupany Prediction Enabling Fine-grained HVAC Control
Much of the energy consumption in buildings is due to HVAC systems, which has motivated several recent studies on making these systems more energy- efficient.
