arXiv subjects

Saturnino Luz

Publications and source records attributed to Saturnino Luz.

23 records · Page 2Linked to original sources

arXiv2020

Emotion Recognition in Low-Resource Settings: An Evaluation of Automatic Feature Selection Methods

Research in automatic affect recognition has seldom addressed the issue of computational resource utilization. With the advent of ambient intelligence technology which employs a variety of low-power, resource-constrained devices, this issue is increasingly gaining interest. This is especially the case in the context of health and elderly care technologies, where interventions may rely on monitoring of emotional status to provide support or alert carers as appropriate. This paper focuses on emotion recognition from speech data, in settings where it is desirable to minimize memory and computational requirements. Reducing the number of features for inductive inference is a route towards this goal. In this study, we evaluate three different state-of-the-art feature selection methods: Infinite Latent Feature Selection (ILFS), ReliefF and Fisher (generalized Fisher score), and compare them to our recently proposed feature selection method named `Active Feature Selection' (AFS). The evaluation is performed on three emotion recognition data sets (EmoDB, SAVEE and EMOVO) using two standard acoustic paralinguistic feature sets (i.e. eGeMAPs and emobase). The results show that similar or better accuracy can be achieved using subsets of features substantially smaller than the entire feature set. A machine learning model trained on a smaller feature set will reduce the memory and computational resources of an emotion recognition system which can result in lowering the barriers for use of health monitoring technology.

cs.LG↗

arXiv2020

AttViz: Online exploration of self-attention for transparent neural language modeling

Neural language models are becoming the prevailing methodology for the tasks of query answering, text classification, disambiguation, completion and translation. Commonly comprised of hundreds of millions of parameters, these neural network models offer state-of-the-art performance at the cost of interpretability; humans are no longer capable of tracing and understanding how decisions are being made. The attention mechanism, introduced initially for the task of translation, has been successfully adopted for other language-related tasks. We propose AttViz, an online toolkit for exploration of self-attention---real values associated with individual text tokens. We show how existing deep learning pipelines can produce outputs suitable for AttViz, offering novel visualizations of the attention heads and their aggregations with minimal effort, online. We show on examples of news segments how the proposed system can be used to inspect and potentially better understand what a model has learned (or emphasized).

cs.LG↗

arXiv2019

Potential Applications of Machine Learning at Multidisciplinary Medical Team Meetings

While machine learning (ML) systems have produced great advances in several domains, their use in support of complex cooperative work remains a research challenge. A particularly challenging setting, and one that may benefit from ML support is the work of multidisciplinary medical teams (MDTs). This paper focuses on the activities performed during the multidisciplinary medical team meeting (MDTM), reviewing their main characteristics in light of a longitudinal analysis of several MDTs in a large teaching hospital over a period of ten years and of our development of ML methods to support MDTMs, and identifying opportunities and possible pitfalls for the use of ML to support MDTMs.

cs.AI↗

arXiv2018

A Method for Analysis of Patient Speech in Dialogue for Dementia Detection

We present an approach to automatic detection of Alzheimer's type dementia based on characteristics of spontaneous spoken language dialogue consisting of interviews recorded in natural settings. The proposed method employs additive logistic regression (a machine learning boosting method) on content-free features extracted from dialogical interaction to build a predictive model. The model training data consisted of 21 dialogues between patients with Alzheimer's and interviewers, and 17 dialogues between patients with other health conditions and interviewers. Features analysed included speech rate, turn-taking patterns and other speech parameters. Despite relying solely on content-free features, our method obtains overall accuracy of 86.5\%, a result comparable to those of state-of-the-art methods that employ more complex lexical, syntactic and semantic features. While further investigation is needed, the fact that we were able to obtain promising results using only features that can be easily extracted from spontaneous dialogues suggests the possibility of designing non-invasive and low-cost mental health monitoring tools for use at scale.

eess.AS↗

arXiv2017

An Application of Mosaic Diagrams to the Visualization of Set Relationships

We present an application of mosaic diagrams to the visualisation of set relations. Venn and Euler diagrams are the best known visual representations of sets and their relationships (intersections, containment or subsets, exclusion or disjointness). In recent years, alternative forms of visualisation have been proposed. Among them, linear diagrams have been shown to compare favourably to Venn and Euler diagrams, in supporting non-interactive assessment of set relationships. Recent studies that compared several variants of linear diagrams have demonstrated that users perform best at tasks involving identification of intersections, disjointness and subsets when using a horizontally drawn linear diagram with thin lines representing sets, and employing vertical lines as guide lines. The essential visual task the user needs to perform in order to interpret this kind of diagram is vertical alignment of parallel lines and detection of overlaps. Space-filling mosaic diagrams which support this same visual task have been used in other applications, such as the visualization of schedules of activities, where they have been shown to be superior to linear Gantt charts. In this paper, we present an application of mosaic diagrams for visualization of set relationships, and compare it to linear diagrams in terms of accuracy, time-to-answer, and subjective ratings of perceived task difficulty. The study participants exhibited similar performance on both visualisations, suggesting that mosaic diagrams are a good alternative to Venn and Euler diagrams, and that the choice between linear diagrams and mosaics may be solely guided by visual design considerations.

cs.GR↗