ALS is a fatal neurodegenerative disease with no cure. Experts typically measure disease progression via the ALSFRS-R score, which includes measurements of various abilities known to decline. We propose instead the use of speech analysis as a proxy for ALS progression. This technique enables 1) frequent non-invasive, inexpensive, longitudinal analysis, 2) analysis of data recorded in the wild, and 3) creation of an extensive ALS databank for future analysis. Patients and trained medical professionals need not be co-located, enabling more frequent monitoring of more patients from the convenience of their own homes. The goals of this study are the identification of acoustic speech features in naturalistic contexts which characterize disease progression and development of machine models which can recognize the presence and severity of the disease. We evaluated subjects from the Prize4Life Israel dataset, using a variety of frequency, spectral, and voice quality features. The dataset was generated using the ALS Mobile Analyzer, a cellphone app that collects data regarding disease progress using a self-reported ALSFRS-R questionnaire and several active tasks that measure speech and motor skills. Classification via leavefive-subjects-out cross-validation resulted in an accuracy rate of 79% (61% chance) for males and 83% (52% chance) for females.

The diagnosis and treatment of psychiatric disorders depends on the analysis of behavior through language by a clinical specialist. This analysis is subjective in nature and could benefit from automated, objective acoustic and linguistic processing methods. This integrated approach would convey a richer representation of patient speech, particularly for expression of emotion. In this work, we explore the potential of acoustic and prosodic metrics to infer clinical variables and predict psychosis, a condition which produces measurable derailment and tangentiality in patient language. To that purpose, we analyzed the recordings of 32 young patients at high risk of developing clinical psychosis.

No abstract

CrowdBand, a sound composition system, demonstrates how a crowd can create works that meet requested criteria and fulfill the aesthetic character given by keyword description and examples. CrowdBand allows flexibility in music composition in terms of duration of the music, completion time and cost of music composition by giving the requestor two modes - thrifty and normal. CrowdBand’s workflow divides the composition task into three sections: requesting fundamental sounds, assembling sounds into compositions, and evaluating the results. Based on the crowd workers’ responses, we conclude that crowdsourced workers who are non-musicians can design sound and create novel sound compositions through CrowdBand. We also conclude that CrowdBand gives the musically-untrained crowd workers the ability to use common compositional techniques, such as sound layering, vertical stacking of sounds to create harmonic effects, related melodic lines (contrapuntal techniques), and transitions between aesthetic notions, or sound themes. Finally, we show improved, faster results with successive simplification and examples.

No abstract