Sara Khalifa

Thejan Rajapakshe, Rajib Rana, Sara Khalifa et al.

Computers can understand and then engage with people in an emotionally intelligent way thanks to speech-emotion recognition (SER). However, the performance of SER in cross-corpus and real-world live data feed scenarios can be significantly improved. The inability to adapt an existing model to a new domain is one of the shortcomings of SER methods. To address this challenge, researchers have developed domain adaptation techniques that transfer knowledge learnt by a model across the domain. Although existing domain adaptation techniques have improved performances across domains, they can be improved to adapt to a real-world live data feed situation where a model can self-tune while deployed. In this paper, we present a deep reinforcement learning-based strategy (RL-DA) for adapting a pre-trained model to a real-world live data feed setting while interacting with the environment and collecting continual feedback. RL-DA is evaluated on SER tasks, including cross-corpus and cross-language domain adaption schema. 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.

Thejan Rajapakshe, Rajib Rana, Sara Khalifa et al.

Speech Emotion Recognition (SER) is crucial for enabling computers to understand the emotions conveyed in human communication. With recent advancements in Deep Learning (DL), the performance of SER models has significantly improved. However, designing an optimal DL architecture requires specialised knowledge and experimental assessments. Fortunately, Neural Architecture Search (NAS) provides a potential solution for automatically determining the best DL model. The Differentiable Architecture Search (DARTS) is a particularly efficient method for discovering optimal models. This study presents emoDARTS, a DARTS-optimised joint CNN and Sequential Neural Network (SeqNN: LSTM, RNN) architecture that enhances SER performance. The literature supports the selection of CNN and LSTM coupling to improve performance. While DARTS has previously been used to choose CNN and LSTM operations independently, our technique adds a novel mechanism for selecting CNN and SeqNN operations in conjunction using DARTS. Unlike earlier work, we do not impose limits on the layer order of the CNN. Instead, we let DARTS choose the best layer order inside the DARTS cell. We demonstrate that emoDARTS outperforms conventionally designed CNN-LSTM models and surpasses the best-reported SER results achieved through DARTS on CNN-LSTM by evaluating our approach on the IEMOCAP, MSP-IMPROV, and MSP-Podcast datasets.

Ahmed Akl, Abdelwahed Khamis, Ali Cheraghian et al.

Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal understanding capabilities, yet they remain prone to object hallucination, where models describe non-existent objects or attribute incorrect factual information, raising serious concerns for reliable real-world deployment. While fine-tuning is a commonly adopted mitigation strategy, its high computational cost and practical difficulty motivate the need for training-free alternatives, among which model editing has recently emerged as a promising direction. However, indiscriminate editing risks disrupting the rich implicit knowledge encoded in pre-trained LVLMs, leading to a fundamental question: how much intervention is necessary at each layer to suppress hallucinations while preserving pre-trained knowledge? To address this question, we present a systematic analysis of LVLM decoders built on three widely used large language model backbones-Qwen, LLaMA, and Vicuna-revealing clear layer-wise differences in susceptibility to object hallucination. Building on these insights, we introduce the Hallucination Insensitivity Score (HIS), a principled metric that quantifies each layer's sensitivity to hallucination and provides guidance for targeted intervention. Leveraging HIS, we propose Hallucination Insensitivity Model Editing (HIME), a simple yet effective layer-adaptive weight editing approach that selectively modifies latent features to suppress hallucinations while preserving pre-trained knowledge. Extensive experiments demonstrate that HIME reduces hallucinations by an average of 61.8% across open-ended generation benchmarks, including CHAIR, MME, and GPT-4V-aided evaluation, without introducing additional parameters, inference-time latency, or computational overhead.

Mohammed Osman Gani, Zhipeng He, Chun Ouyang et al.

Accurate electricity price forecasting (EPF) is essential for operational planning, trading, and flexible asset scheduling in liberalised power systems, yet remains challenging due to volatility, heavy-tailed spikes, and frequent regime shifts. While deep learning (DL) has been increasingly adopted in EPF to capture complex and nonlinear price dynamics, several important gaps persist: (i) limited attention to multi-day horizons beyond day-ahead forecasting, (ii) insufficient exploration of state-of-the-art (SOTA) time series DL models, and (iii) a predominant reliance on aggregated horizon-level evaluation that obscures time-of-day forecasting variation. To address these gaps, we propose a novel EPF framework that extends the forecast horizon to multi-day-ahead by systematically building forecasting models that leverage benchmarked SOTA time series DL models. We conduct a comprehensive evaluation to analyse time-of-day forecasting performance by integrating model assessment at intraday interval levels across all five regions in the Australian National Electricity Market (NEM). The results show that no single model consistently dominates across regions, metrics, and horizons. Overall, standard DL models deliver superior performance in most regions, while SOTA time series DL models demonstrate greater robustness to forecast horizon extension. Intraday interval-level evaluation reveals pronounced diurnal error patterns, indicating that absolute errors peak during the evening ramp, relative errors inflate during midday negative-price regimes, and directional accuracy degrades during periods of frequent trend changes. These findings suggest that future research on DL-based EPF can benefit from enriched feature representations and modelling strategies that enhance longer-term forecasting robustness while maintaining sensitivity to intraday volatility and structural price dynamics.

Abdelwahed Khamis, Sara Khalifa

Real-world sensing challenges such as sensor failures, communication issues, and power constraints lead to data intermittency. An issue that is known to undermine the traditional classification task that assumes a continuous data stream. Previous works addressed this issue by designing bespoke solutions (i.e. task-specific and/or modality-specific imputation). These approaches, while effective for their intended purposes, had limitations in their applicability across different tasks and sensor modalities. This raises an important question: Can we build a task-agnostic imputation pipeline that is transferable to new sensors without requiring additional training? In this work, we formalise the concept of zero-shot imputation and propose a novel approach that enables the adaptation of pre-trained models to handle data intermittency. This framework, named NeuralPrefix, is a generative neural component that precedes a task model during inference, filling in gaps caused by data intermittency. NeuralPrefix is built as a continuous dynamical system, where its internal state can be estimated at any point in time by solving an Ordinary Differential Equation (ODE). This approach allows for a more versatile and adaptable imputation method, overcoming the limitations of task-specific and modality-specific solutions. We conduct a comprehensive evaluation of NeuralPrefix on multiple sensory datasets, demonstrating its effectiveness across various domains. When tested on intermittent data with a high 50% missing data rate, NeuralPreifx accurately recovers all the missing samples, achieving SSIM score between 0.93-0.96. Zero-shot evaluations show that NeuralPrefix generalises well to unseen datasets, even when the measurements come from a different modality.

Thejan Rajapakshe, Rajib Rana, Farina Riaz et al.

Quantum machine learning (QML) offers a promising avenue for advancing representation learning in complex signal domains. In this study, we investigate the use of parameterised quantum circuits (PQCs) for speech emotion recognition (SER) a challenging task due to the subtle temporal variations and overlapping affective states in vocal signals. We propose a hybrid quantum classical architecture that integrates PQCs into a conventional convolutional neural network (CNN), leveraging quantum properties such as superposition and entanglement to enrich emotional feature representations. Experimental evaluations on three benchmark datasets IEMOCAP, RECOLA, and MSP-IMPROV demonstrate that our hybrid model achieves improved classification performance relative to a purely classical CNN baseline, with over 50% reduction in trainable parameters. This work provides early evidence of the potential for QML to enhance emotion recognition and lays the foundation for future quantum-enabled affective computing systems.

Ahmed Akl, Abdelwahed Khamis, Zhe Wang et al.

Visual Question Answering (VQA) systems are known for their poor performance in out-of-distribution datasets. An issue that was addressed in previous works through ensemble learning, answer re-ranking, or artificially growing the training set. In this work, we show for the first time that robust Visual Question Answering is attainable by simply enhancing the training strategy. Our proposed approach, Task Progressive Curriculum Learning (TPCL), breaks the main VQA problem into smaller, easier tasks based on the question type. Then, it progressively trains the model on a (carefully crafted) sequence of tasks. We further support the method by a novel distributional-based difficulty measurer. Our approach is conceptually simple, model-agnostic, and easy to implement. We demonstrate TPCL effectiveness through a comprehensive evaluation on standard datasets. Without either data augmentation or explicit debiasing mechanism, it achieves state-of-the-art on VQA-CP v2, VQA-CP v1 and VQA v2 datasets. Extensive experiments demonstrate that TPCL outperforms the most competitive robust VQA approaches by more than 5% and 7% on VQA-CP v2 and VQA-CP v1; respectively. TPCL also can boost VQA baseline backbone performance by up to 28.5%.

Thejan Rajapakshe, Rajib Rana, Sara Khalifa et al.

Speech Emotion Recognition (SER) is a critical enabler of emotion-aware communication in human-computer interactions. Recent advancements in Deep Learning (DL) have substantially enhanced the performance of SER models through increased model complexity. However, designing optimal DL architectures requires prior experience and experimental evaluations. Encouragingly, Neural Architecture Search (NAS) offers a promising avenue to determine an optimal DL model automatically. In particular, Differentiable Architecture Search (DARTS) is an efficient method of using NAS to search for optimised models. This paper proposes a DARTS-optimised joint CNN and LSTM architecture, to improve SER performance, where the literature informs the selection of CNN and LSTM coupling to offer improved performance. While DARTS has previously been applied to CNN and LSTM combinations, our approach introduces a novel mechanism, particularly in selecting CNN operations using DARTS. 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. Experimenting with the IEMOCAP and MSP-IMPROV datasets, we demonstrate that our proposed methodology achieves significantly higher SER accuracy than hand-engineering the CNN-LSTM configuration. It also outperforms the best-reported SER results achieved using DARTS on CNN-LSTM.

Thejan Rajapakshe, Rajib Rana, Sara Khalifa et al.

Reinforcement Learning (RL) is a semi-supervised learning paradigm which an agent learns by interacting with an environment. Deep learning in combination with RL provides an efficient method to learn how to interact with the environment is called Deep Reinforcement Learning (deep RL). Deep RL has gained tremendous success in gaming - such as AlphaGo, but its potential have rarely being explored for challenging tasks like Speech Emotion Recognition (SER). The deep RL being used for SER can potentially improve the performance of an automated call centre agent by dynamically learning emotional-aware response to customer queries. While the policy employed by the RL agent plays a major role in action selection, there is no current RL policy tailored for SER. In addition, extended learning period is a general challenge for deep RL which can impact the speed of learning for SER. Therefore, in this paper, we introduce a novel policy - "Zeta policy" which is tailored for SER and apply Pre-training in deep RL to achieve faster learning rate. Pre-training with cross dataset was also studied to discover the feasibility of pre-training the RL Agent with a similar dataset in a scenario of where no real environmental data is not available. IEMOCAP and SAVEE datasets were used for the evaluation with the problem being to recognize four emotions happy, sad, angry and neutral in the utterances provided. Experimental results show that the proposed "Zeta policy" performs better than existing policies. The results also support that pre-training can reduce the training time upon reducing the warm-up period and is robust to cross-corpus scenario.

Thejan Rajapakshe, Siddique Latif, Rajib Rana et al.

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 tasks, such as playing the game "Go", that were previously difficult to solve. However, deep RL requires significant training time making it difficult to use in various real-life applications such as Human-Computer Interaction (HCI). In this paper, we study pre-training in deep RL to reduce the training time and improve the performance of Speech Recognition, a popular application of HCI. To evaluate the performance improvement in training we use the publicly available "Speech Command" dataset, which contains utterances of 30 command keywords spoken by 2,618 speakers. Results show that pre-training with deep RL offers faster convergence compared to non-pre-trained RL while achieving improved speech recognition accuracy.

Siddique Latif, Rajib Rana, Sara Khalifa et al.

Speech emotion recognition systems (SER) can achieve high accuracy when the training and test data are identically distributed, but this assumption is frequently violated in practice and the performance of SER systems plummet against unforeseen data shifts. The design of robust models for accurate SER is challenging, which limits its use in practical applications. In this paper we propose a deeper neural network architecture wherein we fuse DenseNet, LSTM and Highway Network to learn powerful discriminative features which are robust to noise. We also propose data augmentation with our network architecture to further improve the robustness. We comprehensively evaluate the architecture coupled with data augmentation against (1) noise, (2) adversarial attacks and (3) cross-corpus settings. Our evaluations on the widely used IEMOCAP and MSP-IMPROV datasets show promising results when compared with existing studies and state-of-the-art models.

Siddique Latif, Muhammad Asim, Rajib Rana et al.

Generative adversarial networks (GANs) have shown potential in learning emotional attributes and generating new data samples. However, their performance is usually hindered by the unavailability of larger speech emotion recognition (SER) data. In this work, we propose a framework that utilises the mixup data augmentation scheme to augment the GAN in feature learning and generation. To show the effectiveness of the proposed framework, we present results for SER on (i) synthetic feature vectors, (ii) augmentation of the training data with synthetic features, (iii) encoded features in compressed representation. Our results show that the proposed framework can effectively learn compressed emotional representations as well as it can generate synthetic samples that help improve performance in within-corpus and cross-corpus evaluation.

Siddique Latif, Rajib Rana, Sara Khalifa et al.

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. There are two main drawbacks to this approach: firstly, the feature engineering being manual is cumbersome and requires human knowledge; and secondly, the designed features might not be best for the objective at hand. This has motivated the adoption of a recent trend in speech community towards utilisation of representation learning techniques, which can learn an intermediate representation of the input signal automatically that better suits the task at hand and hence lead to improved performance. The significance of representation learning has increased with advances in deep learning (DL), where the representations are more useful and less dependent on human knowledge, making it very conducive for tasks like classification, prediction, etc. The main contribution of this paper is to present an up-to-date and comprehensive survey on different techniques of speech representation learning by bringing together the scattered research across three distinct research areas including Automatic Speech Recognition (ASR), Speaker Recognition (SR), and Speaker Emotion Recognition (SER). Recent reviews in speech have been conducted for ASR, SR, and SER, however, none of these has focused on the representation learning from speech -- a gap that our survey aims to bridge.

Thejan Rajapakshe, Rajib Rana, Siddique Latif et al.

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 led to breakthroughs in many complex tasks that were previously difficult to solve. However, deep RL requires a large amount of training time that makes it difficult to use in various real-life applications like human-computer interaction (HCI). Therefore, in this paper, we study pre-training in deep RL to reduce the training time and improve the performance in speech recognition, a popular application of HCI. We achieve significantly improved performance in less time on a publicly available speech command recognition dataset.

Siddique Latif, Rajib Rana, Sara Khalifa et al.

Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the scarcity of emotion datasets, which is a challenge for developing any robust machine learning model in general. In this paper, we propose a solution to this problem: a multi-task learning framework that uses auxiliary tasks for which data is abundantly available. We show that utilisation of this additional data can improve the primary task of SER for which only limited labelled data is available. In particular, we use gender identifications and speaker recognition as auxiliary tasks, which allow the use of very large datasets, e.g., speaker classification datasets. To maximise the benefit of multi-task learning, we further use an adversarial autoencoder (AAE) within our framework, which has a strong capability to learn powerful and discriminative features. Furthermore, the unsupervised AAE in combination with the supervised classification networks enables semi-supervised learning which incorporates a discriminative component in the AAE unsupervised training pipeline. This semi-supervised learning essentially helps to improve generalisation of our framework and thus leads to improvements in SER performance. The proposed model is rigorously evaluated for categorical and dimensional emotion, and cross-corpus scenarios. Experimental results demonstrate that the proposed model achieves state-of-the-art performance on two publicly available datasets.

Siddique Latif, Rajib Rana, Sara Khalifa et al.

Speech emotion recognition is a challenging task and heavily depends on hand-engineered acoustic features, which are typically crafted to echo human perception of speech signals. However, a filter bank that is designed from perceptual evidence is not always guaranteed to be the best in a statistical modelling framework where the end goal is for example emotion classification. This has fuelled the emerging trend of learning representations from raw speech especially using deep learning neural networks. In particular, a combination of Convolution Neural Networks (CNNs) and Long Short Term Memory (LSTM) have gained great traction for the intrinsic property of LSTM in learning contextual information crucial for emotion recognition; and CNNs been used for its ability to overcome the scalability problem of regular neural networks. In this paper, we show that there are still opportunities to improve the performance of emotion recognition from the raw speech by exploiting the properties of CNN in modelling contextual information. We propose the use of parallel convolutional layers to harness multiple temporal resolutions in the feature extraction block that is jointly trained with the LSTM based classification network for the emotion recognition task. Our results suggest that the proposed model can reach the performance of CNN trained with hand-engineered features from both IEMOCAP and MSP-IMPROV datasets.

Guohao Lan, Weitao Xu, Dong Ma et al.

Monitoring the daily transportation modes of an individual provides useful information in many application domains, such as urban design, real-time journey recommendation, as well as providing location-based services. In existing systems, accelerometer and GPS are the dominantly used signal sources for transportation context monitoring which drain out the limited battery life of the wearable devices very quickly. To resolve the high energy consumption issue, in this paper, we present EnTrans, which enables transportation mode detection by using only the kinetic energy harvester as an energy-efficient signal source. The proposed idea is based on the intuition that the vibrations experienced by the passenger during traveling with different transportation modes are distinctive. Thus, voltage signal generated by the energy harvesting devices should contain sufficient features to distinguish different transportation modes. We evaluate our system using over 28 hours of data, which is collected by eight individuals using a practical energy harvesting prototype. The evaluation results demonstrate that EnTrans is able to achieve an overall accuracy over 92% in classifying five different modes while saving more than 34% of the system power compared to conventional accelerometer-based approaches.