Tjeerd Andringa

How Pleasant Sounds Promote and Annoying Sounds Impede Health: A Cognitive Approach

This theoretical paper addresses the cognitive functions via which quiet and in general pleasurable sounds promote and annoying sounds impede health. The article comprises a literature analysis and an interpretation of how the bidirectional influence of appraising the environment and the feelings of the perceiver can be understood in terms of core affect and motivation. This conceptual basis allows the formulation of a detailed cognitive model describing how sonic content, related to indicators of safety and danger, either allows full freedom over mind-states or forces the activation of a vigilance function with associated arousal. The model leads to a number of detailed predictions that can be used to provide existing soundscape approaches with a solid cognitive science foundation that may lead to novel approaches to soundscape design. These will take into account that louder sounds typically contribute to distal situational awareness while subtle environmental sounds provide proximal situational awareness. The role of safety indicators, mediated by proximal situational awareness and subtle sounds, should become more important in future soundscape research.

Disambiguating sound through context

A central problem in automatic sound recognition is the mapping between low-level audio features and the meaningful content of an auditory scene. We propose a dynamic network model to perform this mapping. In acoustics, much research is devoted to low-level perceptual abilities such as audio feature extraction and grouping, which are translated into successful signal processing techniques. However, little work is done on modeling knowledge and context in sound recognition, although this information is necessary to identify a sound event rather than to separate its components from a scene. We first investigate the role of context in human sound identification in a simple experiment. Then we show that the use of knowledge in a dynamic network model can improve automatic sound identification by reducing the search space of the low-level audio features. Furthermore, context information dissolves ambiguities that arise from multiple interpretations of one sound event.

Perceptual Restoration of Degraded Speech Is Preserved with Advancing Age

Cognitive skills, such as processing speed, memory functioning, and the ability to divide attention, are known to diminish with aging. The present study shows that, despite these changes, older adults can successfully compensate for degradations in speech perception. Critically, the older participants of this study were not pre-selected for high performance on cognitive tasks, but only screened for normal hearing. We measured the compensation for speech degradation using phonemic restoration, where intelligibility of degraded speech is enhanced using top-down repair mechanisms. Linguistic knowledge, Gestalt principles of perception, and expectations based on situational and linguistic context are used to effectively fill in the inaudible masked speech portions. A positive compensation effect was previously observed only with young normal hearing people, but not with older hearing-impaired populations, leaving the question whether the lack of compensation was due to aging or due to age-related hearing problems. Older participants in the present study showed poorer intelligibility of degraded speech than the younger group, as expected from previous reports of aging effects. However, in conditions that induce top-down restoration, a robust compensation was observed. Speech perception by the older group was enhanced, and the enhancement effect was similar to that observed with the younger group. This effect was even stronger with slowed-down speech, which gives more time for cognitive processing. Based on previous research, the likely explanations for these observations are that older adults can overcome age-related cognitive deterioration by relying on linguistic skills and vocabulary that they have accumulated over their lifetime. Alternatively, or simultaneously, they may use different cerebral activation patterns or exert more mental effort. This positive finding on top-down restoration skills by the older individuals suggests that new cognitive training methods can teach older adults to effectively use compensatory mechanisms to cope with the complex listening environments of everyday life.

Sound event recognition through expectancy-based evaluation ofsignal-driven hypotheses

A recognition system for environmental sounds is presented. Signal-driven classification is performed by applying machine-learning techniques on features extracted from a cochleogram. These possibly unreliable classifications are improved by creating expectancies of sound events based on context information.

Verbal aggression detection in complex social environments

The paper presents a knowledge-based system designed to detect evidence of aggression by means of audio analysis. The detection is based on the way sounds are analyzed and how they attract attention in the human auditory system. The performance achieved is comparable to human performance in complex social environments. The SIgard system has been deployed in a number of different real-life situations and was tested extensively in the inner city of Groningen. Experienced police observers have annotated ~1400 recordings with various degrees of shouting, which were used for optimization. All essential events and a small number of nonessential aggressive events were detected. The system produces only a few false alarms (non-shouts) per microphone per year and misses no incidents. This makes it the first successful detection system for a non-trivial target in an unconstrained environment.

Positioning soundscape research and management

This paper is an outcome of a workshop that addressed the question how soundscape research can improve its impact on the local level. It addresses a number of topics by complementing existing approaches and practices with possible future approaches and practices. The paper starts with an analysis of the role of sound annoyance and suboptimal soundscapes on the lives of individuals and concludes that a good soundscape, or more generally a good sensescape, is at the same time pleasant as well as conducive for the adoption of healthy habits. To maintain or improve sensescape quality, urban planning needs improved design tools that allow for a more holistic optimization and an active role of the local stakeholders. Associated with this is a gradual development from government to governance in which optimization of the soundscape at a local (administrative or geographic) level is directly influenced by the users of spaces. The paper concludes that soundscape research can have a greater impact by helping urban planners design for health and pleasant experiences as well as developing tools for improved citizen involvement in local optimization.

Why Don't You See What I Mean? Prospects and Limitations of Current Automatic Sign Recognition Research

This article presents an overview of current automatic sign recognition research. A review of recent studies, as well as on our own research, has identified several problem areas that hamper successful sign recognition by a computer. Some of these problems are shared with automatic speech recognition, whereas others seem to be unique to automatic sign recognition. These latter difficulties include context dependency, determination of the basic units of modeling, the ability to distinguish between signs and gestures, movement epenthesis, and repetition within signs. As a possible solution to these problems, bottom-up processing should perhaps be supplemented with top-down processing.

Multi-modal human aggression detection

A system to monitor aggression in surveillance scenes from audio and video.Person motion and proximity measured in volumetric representation of tracked people.Informative sound classes are extracted in challenging acoustic conditions.DBN fuses context and the multi-modal features into latent aggression estimate.Comparison to previous work and system parts shows benefit of combining modalities. This paper presents a smart surveillance system named CASSANDRA, aimed at detecting instances of aggressive human behavior in public environments. A distinguishing aspect of CASSANDRA is the exploitation of complementary audio and video cues to disambiguate scene activity in real-life environments. From the video side, the system uses overlapping cameras to track persons in 3D and to extract features regarding the limb motion relative to the torso. From the audio side, it classifies instances of speech, screaming, singing, and kicking-object. The audio and video cues are fused with contextual cues (interaction, auxiliary objects); a Dynamic Bayesian Network (DBN) produces an estimate of the ambient aggression level.Our prototype system is validated on a realistic set of scenarios performed by professional actors at an actual train station to ensure a realistic audio and video noise setting.

Disambiguating Sounds through Context

A central problem in automatic sound recognition is the mapping between low-level audio features and the meaningful content of an auditory scene. We propose a dynamic network model to perform this mapping. In acoustics, much research has been devoted to low-level perceptual abilities such as audio feature extraction and grouping, which have been translated into successful signal processing techniques. However, little work is done on modeling knowledge and context in sound recognition, although this information is necessary to identify a sound event rather than to separate its components from a scene. We first investigate the role of context in human sound identification in a simple experiment. Then we show that the use of knowledge in a dynamic network model can improve automatic sound identification, by reducing the search space of the low-level audio features. Furthermore, context information dissolves ambiguities that arise from multiple interpretations of one sound event.

Cognition from life: the two modes of cognition that underlie moral behavior

We argue that the capacity to live life to the benefit of self and others originates in the defining properties of life. These lead to two modes of cognition; the coping mode that is preoccupied with the satisfaction of pressing needs and the co-creation mode that aims at the realization of a world where pressing needs occur less frequently. We have used the Rule of Conservative Changes – stating that new functions can only scaffold on evolutionary older, yet highly stable functions – to predict that the interplay of these two modes define a number of core functions in psychology associated with moral behavior. We explore this prediction with five examples reflecting different theoretical approaches to human cognition and action selection. We conclude the paper with the observation that science is currently dominated by the coping mode and that the benefits of the co-creation mode may be necessary to generate realistic prospects for a modern synthesis in the sciences of the mind.