Building Autonomous Sensitive Artificial Listeners

This paper describes a substantial effort to build a real-time interactive multimodal dialogue system with a focus on emotional and non-verbal interaction capabilities. The work is motivated by the aim to provide technology with competences in perceiving and producing the emotional and non-verbal behaviours required to sustain a conversational dialogue. We present the Sensitive Artificial Listener (SAL) scenario as a setting which seems particularly suited for the study of emotional and non- verbal behaviour, since it requires only very limited verbal understanding on the part of the machine. This scenario allows us to concentrate on non-verbal capabilities without having to address at the same time the challenges of spoken language understanding, task modeling etc. We first report on three prototype versions of the SAL scenario, in which the behaviour of the Sensitive Artificial Listener characters was determined by a human operator. These prototypes served the purpose of verifying the effectiveness of the SAL scenario and allowed us to collect data required for building system components for analysing and synthesising the respective behaviours. We then describe the fully autonomous integrated real-time system we created, which combines incremental analysis of user behaviour, dialogue management, and synthesis of speaker and listener behaviour of a SAL character displayed as a virtual agent. We discuss principles that should underlie the evaluation of SAL-type systems. Since the system is designed for modularity and reuse, and since it is publicly available, the SAL system has potential as a joint research tool in the affective computing research community.

Building autonomous sensitive artificial listeners (Extended abstract)

This paper describes a substantial effort to build a real-time interactive multimodal dialogue system with a focus on emotional and non-verbal interaction capabilities. The work is motivated by the aim to provide technology with competences in perceiving and producing the emotional and non-verbal behaviours required to sustain a conversational dialogue. We present the Sensitive Artificial Listener (SAL) scenario as a setting which seems particularly suited for the study of emotional and non-verbal behaviour, since it requires only very limited verbal understanding on the part of the machine. This scenario allows us to concentrate on non-verbal capabilities without having to address at the same time the challenges of spoken language understanding, task modeling etc. We first summarise three prototype versions of the SAL scenario, in which the behaviour of the Sensitive Artificial Listener characters was determined by a human operator. These prototypes served the purpose of verifying the effectiveness of the SAL scenario and allowed us to collect data required for building system components for analysing and synthesising the respective behaviours. We then describe the fully autonomous integrated real-time system we created, which combines incremental analysis of user behaviour, dialogue management, and synthesis of speaker and listener behaviour of a SAL character displayed as a virtual agent. We discuss principles that should underlie the evaluation of SAL-type systems. Since the system is designed for modularity and reuse, and since it is publicly available, the SAL system has potential as a joint research tool in the affective computing research community.

Association of retinal arteriolar dilatation with lower verbal memory::The Edinburgh Type 2 Diabetes Study

Abstract


AIMS/HYPOTHESIS:

Retinal vascular calibre changes may reflect early subclinical microvascular disease in diabetes. Because of the considerable homology between retinal and cerebral microcirculation, we examined whether retinal vascular calibre, as a proxy of cerebral microvascular disease, was associated with cognitive function in older people with type 2 diabetes.

METHODS:

A cross-sectional analysis of 954 people aged 60-75 years with type 2 diabetes from the population-based Edinburgh Type 2 Diabetes Study was performed. Participants underwent standard seven-field binocular digital retinal photography and a battery of seven cognitive function tests. The Mill Hill Vocabulary Scale was used to estimate pre-morbid cognitive ability. Retinal vascular calibre was measured from an image field with the optic disc in the centre using a validated computer-based program.

RESULTS:

After age and sex adjustment, larger retinal arteriolar and venular calibres were significantly associated with lower scores for the Wechsler Logical Memory test, with standardised regression coefficients -0.119 and -0.084, respectively (p?<?0.01), but not with other cognitive tests. There was a significant interaction between sex and retinal vascular calibre for logical memory. In male participants, the association of increased retinal arteriolar calibre with logical memory persisted (p?<?0.05) when further adjusted for vocabulary, venular calibre, depression, cardiovascular risk factors and macrovascular disease. In female participants, this association was weaker and not significant.

CONCLUSIONS/INTERPRETATION:

Retinal arteriolar dilatation was associated with poorer memory, independent of estimated prior cognitive ability in older men with type 2 diabetes. The sex interaction with stronger findings in men requires confirmation. Nevertheless, these data suggest that impaired cerebral arteriolar autoregulation in smooth muscle cells, leading to arteriolar dilatation, may be a possible pathogenic mechanism in verbal declarative memory decrements in people with diabetes.