The integration of Artificial Intelligence (AI) across various fields has transformed the educational landscape and demands a targeted approach to teaching AI in an academic setting. As lecturers aim to prepare students for an AI-driven future, they face various challenges arising from the complex and mathematical nature of AI. This paper explores the challenges of teaching and assessing AI modules in large classrooms by implementing a student-centred approach alongside formative assessment and feedback. It also examines issues related to the diversity of students' skill sets and learning style. This study was conducted on two different cohorts of the same module, Video Analytics and Machine Learning during 2022-2024. Two distinct cohorts were chosen to ensure unbiased conclusions in our study. By recognising and actively addressing these challenges, lecturers can more effectively equip students with the skills needed to navigate this rapidly evolving field. In conclusion, this study shows that implementing formative assessments like quizzes and student-centred approaches are highly beneficial in large classrooms and lead to a significant improvement in student performance and learning outcomes. In addition, the analysis shows that students who are more actively engaged with quizzes tend to score higher on the module. While the overall student feedback has been positive and there has been noticeable improvement in performance, it is important to recognise that there have been instances of unsatisfactory student outcomes as well.

User Experience (UX) Design, while not a new term, has become significantly importance in recent years. It includes how users interact with software, focusing not only on completing specific tasks efficiently and error-free, but also on the overall experience. This contains the emotional impact, user satisfaction, and whether the experience was enjoyable and worth recommending to others. However, teaching these concepts within a module in an academic setting presents complications. Students often lack real-world experience that making it harder for them to appreciate how deeply these factors influence user behaviours and product success. In our case study, students registering in this module often come from different cohorts, such as Business Information Technology (BIT) and Computing and Information Technology (CIT). While BIT and CIT pathways both integrate aspects of technology, they serve different educational and career purposes. Teaching UX to these students can be challenging, potentially impacting their performance in the final project-based assignment. These issues can be categorised into theoretical and practical aspects that can be addressed by considering students different learning styles and create a more inclusive and effective learning environment. This paper explores the student-centred approach particularly within the framework of a User Experience Design module. The study was carried out over two academic years of the same module. In the first cohort, only slight modifications were introduced, while the second cohort fully embraced the proposed techniques. The results revealed a significant improvement in the students' final project performance after the full implementation of this approach.

This innovative practice paper presents a work-inprogress on the design of a 'play-kit' to introduce incoming first-year university students to diverse thinking styles through playful interactions, addressing the need for adaptable problemsolving skills development required to tackle increasingly complex global socio-technical challenges. Our initial design stage involves creating a prototype physical workbook to stimulate computational thinking skills through play. We will adapt lessons from existing computational thinking material, originally designed as a classroom-based tool for primary school students. We customize lessons for university students, and re-work them so that they become self-directed learning activities. Our workbook emphasizes essential computational components - decomposition, algorithms, pattern recognition, logic, representation, and abstraction. In time, the project will offer both physical and online 'Learning to Think' play-kits to widen accessibility and suit a diversity of learning styles.

This paper presents the design and implementation of a two-week hackathon at a large prestigious UK university, focused on creating sustainable solutions leveraging generative artificial intelligence (genAI). The hackathon deviated from the traditional one to three-day format, providing an extended period for ideation, development, and public voting. The event aimed to foster innovation, engage the local community in sustainability efforts, and augment participants' problem-solving capabilities through the use of genAI. The hackathon incorporated inclusivity measures based on evidence-based recommendations, ensuring diverse participation and a supportive environment. The participants could choose from four challenges to create a solution around that were based on local sustainability issues: housing regeneration, promoting sustainable and active travel, revitalizing the city center, and increasing re-naturing within the city. Teams were formed using a mix of self-selection and pre-assignment. Participants had access to comprehensive resources, including workshops on jupyter notebooks, genAI, video creation, and support from mentors. The final outputs each team was expected to produce was a 90 second video that detailed the challenge, their proposed solution, how they used open data, how they used genAI either in their solution or in their work process, as well as any files required for their solution to run/compile. The video was also to be used for the public vote, to decide the people's choice award, and hence could be promotional in nature but everyone in the team had to contribute to it in a meaningful way. Thus, they do not have to appear in it but could write a script or edit, etc. Judging criteria focused on the quality of the presentation, creativity, effective use of open data, and engagement with genAI. The event concluded with awards for the most polished solution, most creative idea, best use of open data, best use of genAI, best overall, and a people's choice award decided by a public vote. This paper contributes to the body of knowledge on leveraging genAI for sustainability and offers insights into develoning inclusive and impactful hackathons.

Computer science including data analytics is a widely popular field, boasting promising career opportunities in the future. Proficiency in programming stands as a fundamental requirement for success in this domain. However, students entering MSc programs in data analytics often possess varying levels of programming background, which can impact their performance in assignments. Recognising and addressing these differences through tailored instruction can improve students’ outcomes. This paper explores the importance of considering students' programming backgrounds in the data analytics field and highlights strategies to enhance their performance based on prior knowledge. This study was carried out on two different modules in two different pathways. We have chosen two distinct cohorts and pathways to ensure unbiased conclusions in our study. The initial research was applied to the Database and Programming Fundamentals module for an MSc data analytics cohort, and then we utilized a Deep Learning module for final year computer science undergraduates as a validation cohort. As a conclusion, this study successfully demonstrated a significant increase in student assignment performance through the implementation of tailored instruction based on students' programming backgrounds. Despite receiving positive student feedback and observing excellent and improved performances, it is crucial to acknowledge instances of unsatisfactory student performance as well. Both studies were conducted by the School of Electronics, Electrical Engineering, and Computer Science (EEECS) at Queen's University Belfast (QUB) during the academic year 2021/2022.

Abstract This paper explores the suitability of lip-based authentication as a behavioural biometric for mobile devices. Lip-based biometric authentication is the process of verifying an individual based on visual information taken from the lips while speaking. It is particularly suited to mobile devices because it contains unique information; its potential for liveness over existing popular biometrics such as face and fingerprint and lip movements can be captured using a device’s front-facing camera, requiring no dedicated hardware. Despite its potential, research and progress into lip-based biometric authentication has been significantly slower than other biometrics such as face, fingerprints, or iris.This paper investigates a state-of-the-art approach using a deep Siamese network, trained with the triplet loss for one-shot lip-based biometric authentication with real-world challenges. The proposed system, LipAuth, is rigourously examined with real-world data and challenges that could be expected on lip-based solution deployed on a mobile device. The work in this paper shows for the first time how a lip-based authentication system performs beyond a closed-set protocol, benchmarking a new open-set protocol with an equal error rates of 1.65% on the XM2VTS dataset.New datasets, qFace and FAVLIPS, were collected for the work in this paper, which push the field forward by enabling systematic testing of the content and quantities of data needed for lip-based biometric authentication and highlight problematic areas for future work. The FAVLIPS dataset was designed to mimic some of the hardest challenges that could be expected in a deployment scenario and include varied spoken content, miming and a wide range of challenging lighting conditions. The datasets captured for this work are available to other university research groups on request.

This paper presents the maximum weighted stream posterior (MWSP) model as a robust and efficient stream integration method for audio-visual speech recognition in environments, where the audio or video streams may be subjected to unknown and time-varying corruption. A significant advantage of MWSP is that it does not require any specific measurements of the signal in either stream to calculate appropriate stream weights during recognition, and as such it is modality-independent. This also means that MWSP complements and can be used alongside many of the other approaches that have been proposed in the literature for this problem. For evaluation we used the large XM2VTS database for speaker-independent audio-visual speech recognition. The extensive tests include both clean and corrupted utterances with corruption added in either/both the video and audio streams using a variety of types (e.g., MPEG-4 video compression) and levels of noise. The experiments show that this approach gives excellent performance in comparison to another well-known dynamic stream weighting approach and also compared to any fixed-weighted integration approach in both clean conditions or when noise is added to either stream. Furthermore, our experiments show that the MWSP approach dynamically selects suitable integration weights on a frame-by-frame basis according to the level of noise in the streams and also according to the naturally fluctuating relative reliability of the modalities even in clean conditions. The MWSP approach is shown to maintain robust recognition performance in all tested conditions, while requiring no prior knowledge about the type or level of noise.

In this paper, we present a new approach to visual speech recognition which improves contextual modelling by combining Inter-Frame Dependent and Hidden Markov Models. This approach captures contextual information in visual speech that may be lost using a Hidden Markov Model alone. We apply contextual modelling to a large speaker independent isolated digit recognition task, and compare our approach to two commonly adopted feature based techniques for incorporating speech dynamics. Results are presented from baseline feature based systems and the combined modelling technique. We illustrate that both of these techniques achieve similar levels of performance when used independently. However significant improvements in performance can be achieved through a combination of the two. In particular we report an improvement in excess of 17% relative Word Error Rate in comparison to our best baseline system.

For the first time in this paper we present results showing the effect of speaker head pose angle on automatic lip-reading performance over a wide range of closely spaced angles. We analyse the effect head pose has upon the features themselves and show that by selecting coefficients with minimum variance w.r.t. pose angle, recognition performance can be improved when train-test pose angles differ. Experiments are conducted using the initial phase of a unique multi view Audio-Visual database designed specifically for research and development of pose-invariant lip-reading systems. We firstly show that it is the higher order horizontal spatial frequency components that become most detrimental as the pose deviates. Secondly we assess the performance of different feature selection masks across a range of pose angles including a new mask based on Minimum Cross-Pose Variance coefficients. We report a relative improvement of 50% in Word Error Rate when using our selection mask over a common energy based selection during profile view lip-reading.

For the first time in this paper we present results showing the effect of out of plane speaker head pose variation on a lip based speaker verification system. Using appearance DCT based features, we adopt a Mutual Information analysis technique to highlight the class discriminant DCT components most robust to changes in out of plane pose. Experiments are conducted using the initial phase of a new multi view Audio-Visual database designed for research and development of pose-invariant speech and speaker recognition. We show that verification performance can be improved by substituting higher order horizontal DCT components for vertical, particularly in the case of a train/test pose angle mismatch. We further show that the best performance can be achieved by combining this alternative feature selection with multi view training, reporting a relative 45% Equal Error Rate reduction over a common energy based selection. © 2010 ISCA.

This paper describes the anatomy of a pilot surveillance system with a speech-based interface for content-based retrieval of video data. The proposed system relies on an ontology-based information sharing architecture and lets components of the system communicate among each other through TCP/IP communication channels. The aim of developing the pilot system was to explore dependencies between image analysis, event detection, video annotation, and speech- based retrieval of the video content in the context of a broader spoken dialogue system.

TEST 02 - Elsevier's Scopus, the largest abstract and citation database of peer-reviewed literature. Search and access research from the science, technology, medicine, social sciences and arts and humanities fields.

We consider speaker identification involving background noise, assuming no knowledge about the noise characteristics. A new method, namely universal compensation (UC), is studied as a solution to the problem. The UC method is an extension of the missing-feature method, i.e. recognition based only on reliable data but robust to any corruption type, including full corruption that affects all time-frequency components of the speech representation. The UC technique achieves robustness to unknown, full noise corruption through a novel combination of the multi-condition training method and the missing-feature method. The combination of these two strategies makes the new method potentially capable of dealing with arbitrary additive noise - with arbitrary temporal-spectral characteristics - based only on clean speech training data and simulated noise data, without requiring knowledge about the actual noise. The SPIDRE database is used for the evaluation, assuming various corruptions from real-world noise data. The results obtained are encouraging.

TEST 02 - Elsevier's Scopus, the largest abstract and citation database of peer-reviewed literature. Search and access research from the science, technology, medicine, social sciences and arts and humanities fields.

This paper investigates the effect of modeling subband correlation for noisy speech recognition. Subband feature streams are assumed to be independent in many subband-based speech recognition systems. However, speech recognition experimental results suggest this assumption is unrealistic. In this paper, a method is proposed to incorporate correlation into subband speech feature streams. In the proposed method, all possible combinations of subbands are created and each combination is treated as a single frequency-band by calculating a single feature vector for it. The resulting feature vectors, therefore, capture information about every band in the combination, as well as the dependency across the bands. Although using the new features results in a higher computational complexity, our experimental results show that they effectively capture the correlation between the subbands while making minimal assumptions about the structure of the correlation. Experiments are conducted on the TIDigits database. The results demonstrate improved accuracy for clean speech recognition and improved robustness in the presence of both stationary and nonstationary band-selective noise, in comparison to a system assuming subband independence.

The paper investigates the effect of modeling sub-band correlation for noisy speech recognition. Sub-band data streams are assumed to be independent in many sub-band based speech recognition systems. However, the structure and operation of the human vocal tract suggests this assumption is unrealistic. A novel method is proposed to incorporate correlation into sub-band speech feature streams. All possible combinations of sub-bands are created and each combination is treated as a single frequency band by calculating a single feature vector for it. The resulting feature vectors capture information about every band in the combination as well as the dependency across the bands. Experiments conducted on the TIDigits database demonstrate significantly improved robustness in comparison to an independent sub-band system in the presence of both stationary and non-stationary noise.

Real-world noise may be a mixture of known or trainable noise and unknown unexpected noise. This paper investigates the combination of the conventional noise-reduction techniques with the probabilistic union model to deal with this type of mixed noise for robust speech recognition. In particular, we have developed a multi-environment system to remove the known or trainable acoustic mismatch across different environments. The novelty of this system, in contrast to other multi-environment models, is that the acoustic model for each environment is built upon the probabilistic union model, so that this system is also capable of accommodating further unknown unexpected noise within a specific environment. We have tested the new system for connected digit recognition in different environments, each involving an environment-specific noise and some unknown untrained noise. The results indicate that the new system offers significantly improved performance for the environments involving unknown additional noise, in comparison to a baseline multi-environment system.

Although the discrete cosine transform (DCT) is widely used for feature extraction in pattern recognition, it is shown that it converges slowly for most theoretically smooth functions. A modification of the DCT is described, based on a change of variable, which changes it to a new transform, called the discrete Chebyshev transform (DChT), which converges very rapidly for the same smooth functions. Although this rapid convergence is largely destroyed by the noise in real experimental data, the discrete Chebyshev transform is still generally better than the DCT when the sampling of the data can be selected at nonequidistant points. The improvement over the DCT gives a theoretical explanation for improved speech recognition obtained using Mel feature cepstral coefficients. These choose the sampling frequencies of a DCT to correspond to the human perception of pitch. It is shown that this sampling is similar to the sampling used in the discrete Chebyshev transform.

This paper provides a summary of our recent work on robust speech recognition based on a new statistical approach - the probabilistic union model. In particular, we considered speech recognition involving partial corruption in frequency bands, in time duration, and further in feature components. In all these situations, we assumed no prior knowledge about the corrupting noise, e.g. its band location, occurring time and statistical distribution. The new model characterizes these partial, unknown corruptions based on the union of random events. For the evaluation, we have conducted isolated-word recognition tasks by using both a speaker-independent E-set database and the TiDigits database, each being corrupted by various types of additive noise with unknown, time-varying statistics. The results indicate that the probabilistic union model offers robustness to partial corruption in speech utterances, requiring little or no knowledge about the noise characteristics.

Most current speech recognition systems are built upon a single type of model, e.g. an HMM or certain type of segment based model, and furthermore typically employs only one type of acoustic feature e.g. MFCCs and their variants. This entails that the system may not be robust should the modeling assumptions be violated. Recent research efforts have investigated the use of multi-scale/multi-band acoustic features for robust speech recognition. This paper described a multi-model approach as an alternative and complement to the multi-feature approaches. The multi-model approach seeks a combination of different types of acoustic models, thereby integrating the capabilities of each individual model for capturing discriminative information. An example system built upon the combination of the standard HMM technique with a segment-based modeling technique was implemented. Experiments for both isolated-word and continuous speech recognition have shown improved performances over each of the individual models considered in isolation.