Spira: system for early-detection of respiratory insufficiency by voice audio analysis

• Grant number: 20/06443-5
• Support Opportunities: Regular Research Grants
• Start date: July 01, 2020
• End date: December 31, 2022
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Marcelo Finger
• Grantee: Marcelo Finger
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• City of the host institution: São Paulo
• Associated researchers: Alfredo Goldman vel Lejbman ; Anna Sara Shafferman Levin ; Arnaldo Candido Junior ; Beatriz Raposo de Medeiros ; Ester Cerdeira Sabino ; Flaviane Romani Fernandes Svartman ; Larissa Cristina Berti ; Marcelo Gomes de Queiroz ; Marcus Vinícius Moreira Martins ; Sandra Maria Aluísio
• Associated research grant: 14/12236-1 - AnImaLS: Annotation of Images in Large Scale: what can machines and specialists learn from interaction?, AP.TEM
• Associated scholarship(s): 20/16543-7 - Pre-trained neural models for detecting respiratory insufficiency in speech, BP.PD

Abstract

The aim of this study is to develop a tool that can provide an early detection for people with respiratory insufficiency due to COVID-19, using speech data. To this end, we will collect audio records from infected people as well as normal people, in order to explore differences associated with O2-saturation and respiratory rate that allow the two groups to be distinguished.The proposed automatic classification tool will be based on artificial intelligence, signal processing and machine learning techniques, and will initially serve to facilitate the screening of patients who need to seek medical and hospital assistance. In a second step, the tool can help telemedicine systems to monitor patients continuously, allowing the monitoring of the evolution of inpatients. (AU)

Scientific publications

(4)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

DE SOUZA, JACKSON JOSE; FINGER, MARCELO; DE ARAUJO, JORGE ALBERTO A.; MARANHAO, JULIANO. Selecting and ranking leading cases in Brazilian Supreme Court decisions. KNOWLEDGE ENGINEERING REVIEW, v. 38, p. 18-pg., 2023-06-14. (14/12236-1, 20/06443-5, 19/07665-4)

BERTI, LARISSA CRISTINA; SPAZZAPAN, EVELYN ALVES; QUEIROZ, MARCELO; PEREIRA, PEDRO LEYTON; FERNANDES-SVARTMAN, FLAVIANE ROMANI; DE MEDEIROS, BEATRIZ RAPOSO; MARTINS, MARCUS VINICIUS MOREIRA; FERREIRA, LETICIA SANTIAGO; DA SILVA, INGRID GANDOLFI GOMES; SABINO, ESTER CERDEIRA; et al. Fundamental frequency related parameters in Brazilians with COVID-19. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, v. 153, n. 1, p. 10-pg., 2023-01-01. (20/06443-5, 20/03990-5)

CASANOVA, EDRESSON; CANDIDO JR, ARNALDO; FERNANDES JR, RICARDO CORSO; FINGER, MARCELO; STEFANEL GRIS, LUCAS RAFAEL; PONTI, MOACIR A.; PINTO DA SILVA, DANIEL PEIXOTO; INT SPEECH COMMUN ASSOC. Transfer Learning and Data Augmentation Techniques to the COVID-19 Identification Tasks in ComParE 2021. INTERSPEECH 2021, v. N/A, p. 5-pg., 2021-01-01. (20/06443-5, 14/12236-1, 19/07665-4)

MARCELO FINGER. Inteligência Artificial e os rumos do processamento do português brasileiro. Estudos avançados, v. 35, n. 101, p. 51-72, 2021-04-19. (19/07665-4, 20/06443-5)