Andrew Hines

Asad Ullah, Alessandro Ragano, Andrew Hines

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient pre-training data may not be available. A common approach is cross-lingual pre-training. Instead, we propose to use audio augmentation techniques, namely: pitch variation, noise addition, accented target language and other language speech to pre-train SSRL models in a low resource condition and evaluate phoneme recognition. Our comparisons found that a combined synthetic augmentations (noise/pitch) strategy outperformed accent and language knowledge transfer. Furthermore, we examined the scaling factor of augmented data to achieve equivalent performance to model pre-trained with target domain speech. Our findings suggest that for resource-constrained languages, combined augmentations can be a viable option than other augmentations.

Michael Chinen, Jan Skoglund, Chandan K A Reddy et al.

Non-reference speech quality models are important for a growing number of applications. The VoiceMOS 2022 challenge provided a dataset of synthetic voice conversion and text-to-speech samples with subjective labels. This study looks at the amount of variance that can be explained in subjective ratings of speech quality from metadata and the distribution imbalances of the dataset. Speech quality models were constructed using wav2vec 2.0 with additional metadata features that included rater groups and system identifiers and obtained competitive metrics including a Spearman rank correlation coefficient (SRCC) of 0.934 and MSE of 0.088 at the system-level, and 0.877 and 0.198 at the utterance-level. Using data and metadata that the test restricted or blinded further improved the metrics. A metadata analysis showed that the system-level metrics do not represent the model's system-level prediction as a result of the wide variation in the number of utterances used for each system on the validation and test datasets. We conclude that, in general, conditions should have enough utterances in the test set to bound the sample mean error, and be relatively balanced in utterance count between systems, otherwise the utterance-level metrics may be more reliable and interpretable.

Jack Geraghty, Jiazheng Li, Alessandro Ragano et al.

Audio quality assessment has been widely researched in the signal processing area. Full-reference objective metrics (e.g., POLQA, ViSQOL) have been developed to estimate the audio quality relying only on human rating experiments. To evaluate the audio quality of novel audio processing techniques, researchers constantly need to compare objective quality metrics. Testing different implementations of the same metric and evaluating new datasets are fundamental and ongoing iterative activities. In this paper, we present AQP - an open-source, node-based, light-weight Python pipeline for audio quality assessment. AQP allows researchers to test and compare objective quality metrics helping to improve robustness, reproducibility and development speed. We introduce the platform, explain the motivations, and illustrate with examples how, using AQP, objective quality metrics can be (i) compared and benchmarked; (ii) prototyped and adapted in a modular fashion; (iii) visualised and checked for errors. The code has been shared on GitHub to encourage adoption and contributions from the community.

Michael Chinen, Felicia S. C. Lim, Jan Skoglund et al.

Estimation of perceptual quality in audio and speech is possible using a variety of methods. The combined v3 release of ViSQOL and ViSQOLAudio (for speech and audio, respectively,) provides improvements upon previous versions, in terms of both design and usage. As an open source C++ library or binary with permissive licensing, ViSQOL can now be deployed beyond the research context into production usage. The feedback from internal production teams at Google has helped to improve this new release, and serves to show cases where it is most applicable, as well as to highlight limitations. The new model is benchmarked against real-world data for evaluation purposes. The trends and direction of future work is discussed.

Alcardo Alex Barakabitze, Arslan Ahmad, Rashid Mijumbi et al.

In this paper, we provide a comprehensive review and updated solutions related to 5G network slicing using SDN and NFV. Firstly, we present 5G service quality and business requirements followed by a description of 5G network softwarization and slicing paradigms including essential concepts, history and different use cases. Secondly, we provide a tutorial of 5G network slicing technology enablers including SDN, NFV, MEC, cloud/Fog computing, network hypervisors, virtual machines & containers. Thidly, we comprehensively survey different industrial initiatives and projects that are pushing forward the adoption of SDN and NFV in accelerating 5G network slicing. A comparison of various 5G architectural approaches in terms of practical implementations, technology adoptions and deployment strategies is presented. Moreover, we provide a discussion on various open source orchestrators and proof of concepts representing industrial contribution. The work also investigates the standardization efforts in 5G networks regarding network slicing and softwarization. Additionally, the article presents the management and orchestration of network slices in a single domain followed by a comprehensive survey of management and orchestration approaches in 5G network slicing across multiple domains while supporting multiple tenants. Furthermore, we highlight the future challenges and research directions regarding network softwarization and slicing using SDN and NFV in 5G networks.

Aaryan Shah, Andrew Hines, Alexia Downs et al.

Objective. Clinical AI documentation systems require evaluation methodologies that are clinically valid, economically viable, and sensitive to iterative changes. Methods requiring expert review per scoring instance are too slow and expensive for safe, iterative deployment. We present a case-specific, clinician-authored rubric methodology for clinical AI evaluation and examine whether LLM-generated rubrics can approximate clinician agreement. Materials and Methods. Twenty clinicians authored 1,646 rubrics for 823 clinical cases (736 real-world, 87 synthetic) across primary care, psychiatry, oncology, and behavioral health. Each rubric was validated by confirming that an LLM-based scoring agent consistently scored clinician-preferred outputs higher than rejected ones. Seven versions of an EHR-embedded AI agent for clinicians were evaluated across all cases. Results. Clinician-authored rubrics discriminated effectively between high- and low-quality outputs (median score gap: 82.9%) with high scoring stability (median range: 0.00%). Median scores improved from 84% to 95%. In later experiments, clinician-LLM ranking agreement (tau: 0.42-0.46) matched or exceeded clinician-clinician agreement (tau: 0.38-0.43), attributable to both ceiling compression and LLM rubric improvement. Discussion. This convergence supports incorporating LLM rubrics alongside clinician-authored ones. At roughly 1,000 times lower cost, LLM rubrics enable substantially greater evaluation coverage, while continued clinical authorship grounds evaluation in expert judgment. Ceiling compression poses a methodological challenge for future inter-rater agreement studies. Conclusion. Case-specific rubrics offer a path for clinical AI evaluation that preserves expert judgment while enabling automation at three orders lower cost. Clinician-authored rubrics establish the baseline against which LLM rubrics are validated.

Aaryan Shah, Andrew Hines, Alexia Downs et al.

Clinical AI systems require not just point-in-time evaluation but continuous governance: the ongoing practice of monitoring, evaluating, iterating, and re-evaluating performance throughout deployment. We present an end-to-end framework of governance that integrates rubric validation, live deployment feedback, technical performance monitoring, and cost tracking, with controlled experimentation gating system changes before deployment. Applied to Hyperscribe, an EHR-embedded agent that converts ambient audio into structured chart updates, twenty clinicians authored 1,646 validated rubrics across 823 cases. Seven Hyperscribe versions were evaluated through controlled experiments, with median scores improving from 84% to 95%. Analysis of 107 live feedback entries over three months showed feedback composition shifting from 79% error reports and 14% positive observations to 30% errors and 45% positive observations as engineering interventions resolved failures. Median processing time per audio segment was 8.1 seconds with a 99.6% effective completion rate after retry mechanisms absorbed transient model errors. These results demonstrate that continuous, multi-channel governance of deployed clinical AI is both achievable and effective.

Davoud Shariat Panah, Alessandro Ragano, Dan Barry et al.

This study presents a systematic evaluation of time-frequency feature design for binaural sound source localization (SSL), focusing on how feature selection influences model performance across diverse conditions. We investigate the performance of a convolutional neural network (CNN) model using various combinations of amplitude-based features (magnitude spectrogram, interaural level difference - ILD) and phase-based features (phase spectrogram, interaural phase difference - IPD). Evaluations on in-domain and out-of-domain data with mismatched head-related transfer functions (HRTFs) reveal that carefully chosen feature combinations often outperform increases in model complexity. While two-feature sets such as ILD + IPD are sufficient for in-domain SSL, generalization to diverse content requires richer inputs combining channel spectrograms with both ILD and IPD. Using the optimal feature sets, our low-complexity CNN model achieves competitive performance. Our findings underscore the importance of feature design in binaural SSL and provide practical guidance for both domain-specific and general-purpose localization.

Davoud Shariat Panah, Alessandro N Franciosi, Cormac McCarthy et al.

Asthma is a chronic respiratory condition that affects millions of people worldwide. While this condition can be managed by administering controller medications through handheld inhalers, clinical studies have shown low adherence to the correct inhaler usage technique. Consequently, many patients may not receive the full benefit of their medication. Automated classification of inhaler sounds has recently been studied to assess medication adherence. However, the existing classification models were typically trained using data from specific inhaler types, and their ability to generalize to sounds from different inhalers remains unexplored. In this study, we adapted the wav2vec 2.0 self-supervised learning model for inhaler sound classification by pre-training and fine-tuning this model on inhaler sounds. The proposed model shows a balanced accuracy of 98% on a dataset collected using a dry powder inhaler and smartwatch device. The results also demonstrate that re-finetuning this model on minimal data from a target inhaler is a promising approach to adapting a generic inhaler sound classification model to a different inhaler device and audio capture hardware. This is the first study in the field to demonstrate the potential of smartwatches as assistive technologies for the personalized monitoring of inhaler adherence using machine learning models.

Arslan Ahmad, Atif Bin Mansoor, Alcardo Alex Barakabitze et al.

The Quality of Experience (QoE) based service management remains key for successful provisioning of multimedia services in next-generation networks such as 5G/6G, which requires proper tools for quality monitoring, prediction and resource management where machine learning (ML) can play a crucial role. In this paper, we provide a tutorial on the development and deployment of the QoE measurement and prediction solutions for video streaming services based on supervised learning ML models. Firstly, we provide a detailed pipeline for developing and deploying supervised learning-based video streaming QoE prediction models which covers several stages including data collection, feature engineering, model optimization and training, testing and prediction and evaluation. Secondly, we discuss the deployment of the ML model for the QoE prediction/measurement in the next generation networks (5G/6G) using network enabling technologies such as Software-Defined Networking (SDN), Network Function Virtualization (NFV) and Mobile Edge Computing (MEC) by proposing reference architecture. Thirdly, we present a comparative study of the state-of-the-art supervised learning ML models for QoE prediction of video streaming applications based on multiple performance metrics.

Alessandro Ragano, Emmanouil Benetos, Andrew Hines

Non-intrusive speech quality assessment is a crucial operation in multimedia applications. The scarcity of annotated data and the lack of a reference signal represent some of the main challenges for designing efficient quality assessment metrics. In this paper, we propose two multi-task models to tackle the problems above. In the first model, we first learn a feature representation with a degradation classifier on a large dataset. Then we perform MOS prediction and degradation classification simultaneously on a small dataset annotated with MOS. In the second approach, the initial stage consists of learning features with a deep clustering-based unsupervised feature representation on the large dataset. Next, we perform MOS prediction and cluster label classification simultaneously on a small dataset. The results show that the deep clustering-based model outperforms the degradation classifier-based model and the 3 baselines (autoencoder features, P.563, and SRMRnorm) on TCD-VoIP. This paper indicates that multi-task learning combined with feature representations from unlabelled data is a promising approach to deal with the lack of large MOS annotated datasets.

Andrew Perkis, Christian Timmerer, Sabina Baraković et al.

With the coming of age of virtual/augmented reality and interactive media, numerous definitions, frameworks, and models of immersion have emerged across different fields ranging from computer graphics to literary works. Immersion is oftentimes used interchangeably with presence as both concepts are closely related. However, there are noticeable interdisciplinary differences regarding definitions, scope, and constituents that are required to be addressed so that a coherent understanding of the concepts can be achieved. Such consensus is vital for paving the directionality of the future of immersive media experiences (IMEx) and all related matters. The aim of this white paper is to provide a survey of definitions of immersion and presence which leads to a definition of immersive media experience (IMEx). The Quality of Experience (QoE) for immersive media is described by establishing a relationship between the concepts of QoE and IMEx followed by application areas of immersive media experience. Influencing factors on immersive media experience are elaborated as well as the assessment of immersive media experience. Finally, standardization activities related to IMEx are highlighted and the white paper is concluded with an outlook related to future developments.

Hamed Z. Jahromi, Declan T. Delaney, Andrew Hines

Quality of Experience (QoE) for various types of websites has gained significant attention in recent years. In order to design and evaluate websites, a metric that can estimate a user's experienced quality robustly for diverse content is necessary. SpeedIndex (SI) has been widely adopted to estimate perceived web page loading progress. It measures the speed of rendering pixels for the webpage that is visible in the browser window. This is termed Above-The-Fold (ATF). The influence of animated content on the perception of ATF has been less comprehensively explored. In this paper, we present an experimental design and methodology to measure ATF perception for websites with and without animated elements for various page content categories. We found that pages with animated elements caused people to have more varied perceptions of ATF under different network conditions. Animated content also impacts the page load estimation accuracy of SI for websites. We discuss how the difference in the perception of ATF will impact the QoE management of web applications. We explain the necessity of revisiting the visual assessment of ATF to include the animated contents and improve the robustness of metrics like SI.

Wissam A. Jassim, Jan Skoglund, Michael Chinen et al.

This study compares the performances of different algorithms for coding speech at low bit rates. In addition to widely deployed traditional vocoders, a selection of recently developed generative-model-based coders at different bit rates are contrasted. Performance analysis of the coded speech is evaluated for different quality aspects: accuracy of pitch periods estimation, the word error rates for automatic speech recognition, and the influence of speaker gender and coding delays. A number of performance metrics of speech samples taken from a publicly available database were compared with subjective scores. Results from subjective quality assessment do not correlate well with existing full reference speech quality metrics. The results provide valuable insights into aspects of the speech signal that will be used to develop a novel metric to accurately predict speech quality from generative-model-based coders.

Helard Martinez, Andrew Hines, Mylene C. Q. Farias

The development of audio-visual quality assessment models poses a number of challenges in order to obtain accurate predictions. One of these challenges is the modelling of the complex interaction that audio and visual stimuli have and how this interaction is interpreted by human users. The No-Reference Audio-Visual Quality Metric Based on a Deep Autoencoder (NAViDAd) deals with this problem from a machine learning perspective. The metric receives two sets of audio and video features descriptors and produces a low-dimensional set of features used to predict the audio-visual quality. A basic implementation of NAViDAd was able to produce accurate predictions tested with a range of different audio-visual databases. The current work performs an ablation study on the base architecture of the metric. Several modules are removed or re-trained using different configurations to have a better understanding of the metric functionality. The results presented in this study provided important feedback that allows us to understand the real capacity of the metric's architecture and eventually develop a much better audio-visual quality metric.

Hamed Z. Jahromi, Ivan Bartolec, Edwin Gamboa et al.

Telepresence robots (TPRs) are versatile, remotely controlled vehicles that enable physical presence and human-to-human interaction over a distance. Thanks to improving hardware and dropping price points, TPRs enjoy the growing interest in various industries and application domains. Still, a satisfying experience remains key for their acceptance and successful adoption, not only in terms of enabling remote communication with others, but also in terms of managing robot mobility by means of remote navigation. This paper focuses on the latter aspect of remote operation which has been hitherto neglected. We present the results of an extensive subjective study designed to systematically assess remote navigation Quality of Experience (QoE) in the context of using a TPR live over the Internet. Participants were 'beamed' into a remote office space and asked to perform characteristic TPR remote operation tasks (driving, turning, parking). Visual and control dimensions of their experience were systematically impaired by altering network characteristics (bandwidth, delay and packet loss rate) in a controlled fashion. Our results show that users can differentiate well between visual and navigation/control aspects of their experience. Furthermore, QoE impairment sensitivity varies with the actual task at hand.

Alessandro Ragano, Emmanouil Benetos, Andrew Hines

Audio impairment recognition is based on finding noise in audio files and categorising the impairment type. Recently, significant performance improvement has been obtained thanks to the usage of advanced deep learning models. However, feature robustness is still an unresolved issue and it is one of the main reasons why we need powerful deep learning architectures. In the presence of a variety of musical styles, hand-crafted features are less efficient in capturing audio degradation characteristics and they are prone to failure when recognising audio impairments and could mistakenly learn musical concepts rather than impairment types. In this paper, we propose a new representation of hand-crafted features that is based on the correlation of feature pairs. We experimentally compare the proposed correlation-based feature representation with a typical raw feature representation used in machine learning and we show superior performance in terms of compact feature dimensionality and improved computational speed in the test stage whilst achieving comparable accuracy.