In the following, we aim to provide an overview on what computer audition (CA), i.e., the application of computing for audio processing including “machine listening,” “computational paralinguistics,” and more general speech and sound analysis, but also synthesis, could contribute in this situation. There is, however, broader belief that also other signals including such from sensors on a smartphone could help even in the diagnosis of COVID-19 ( 4), e.g., the heart rate sensor. In particular, in combination with artificial intelligence (AI), one can exploit a powerful tool, which so far has largely been tapped for prediction of COVID-19 spread, and computer vision (CV) approaches in the corona context such as for automatic screening for COVID-19 on CT images ( 2, 3). These include significant public “shut-down” measures to foster “social distancing” in order to slow down and control further spread.Īs research globally is making massive efforts to contribute to better understand and fight the phenomenon from a medical and interdisciplinary point of view, also computer science and engineering in terms of “Digital Health” solutions aim at maximum exploitation of available and realisable means. In the light of this dramatic spread, one is currently internationally witnessing drastic countermeasures that have not been seen in this form over decades in many countries. However, whether there are long-term effects after recovery is yet to be fully researched. The spread of the disease induced by the SARS-CoV-2 or “Corona” virus is assumed to underlie an exponential growth. On March 11, 2020, the WHO declared the disease triggered by the virus-COVID-19-as pandemic. The World Health Organisation's (WHO) office in China was first made aware of the previously unknown SARS-CoV-2 “Corona” virus on the last day(s) of the last year. We come to the conclusion that CA appears ready for implementation of (pre-)diagnosis and monitoring tools, and more generally provides rich and significant, yet so far untapped potential in the fight against COVID-19 spread. We quickly guide further through challenges that need to be faced for real-life usage and limitations also in comparison with non-audio solutions. These include risk assessment and diagnosis based on symptom histograms and their development over time, as well as monitoring of spread, social distancing and its effects, treatment and recovery, and patient well-being. Then, we consider potential use-cases for exploitation. These include the automatic recognition and monitoring of COVID-19 directly or its symptoms such as breathing, dry, and wet coughing or sneezing sounds, speech under cold, eating behaviour, sleepiness, or pain to name but a few. We first survey which types of related or contextually significant phenomena can be automatically assessed from speech or sound. In this contribution, we provide an overview on the potential for computer audition (CA), i.e., the usage of speech and sound analysis by artificial intelligence to help in this scenario. However, tremendous efforts have been made worldwide to counter-steer and control the epidemic by now labelled as pandemic. 7Department of Neurology, Children's Hospital of Chongqing Medical University, Chongqing Medical University, Chongqing, ChinaĪt the time of writing this article, the world population is suffering from more than 2 million registered COVID-19 disease epidemic-induced deaths since the outbreak of the corona virus, which is now officially known as SARS-CoV-2.6Department of Hand Surgery, Wuhan Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.5Department of Plastic Surgery, The Central Hospital of Wuhan, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.4Educational Physiology Laboratory, The University of Tokyo, Tokyo, Japan.2EIHW – Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany.1GLAM – Group on Language, Audio & Music, Imperial College London, London, United Kingdom.Schuller 3, Kun Qian 4, Juan Liu 5, Huaiyuan Zheng 6 and Xiao Li 7
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |