%Aigaion2 BibTeX export from Idiap Publications
%Sunday 14 April 2024 06:11:53 AM

         author = {Nallanthighal, Venkata Srikanth and Mostaani, Zohreh and H{\"{a}}rm{\"{a}}, Aki and Strik, Helmer and Magimai.-Doss, Mathew},
       keywords = {deep neural networks, Respiratory parameters, signal processing, Speech breathing, Speech technology},
       projects = {Idiap, TIPS, TAPAS},
          title = {Deep learning architectures for estimating breathing signal and respiratory parameters from speech recordings},
        journal = {Neural Networks},
         volume = {141},
           year = {2021},
          pages = {211--224},
           issn = {0893-6080},
            doi = {https://doi.org/10.1016/j.neunet.2021.03.029},
       abstract = {Respiration is an essential and primary mechanism for speech production. We first inhale and then produce speech while exhaling. When we run out of breath, we stop speaking and inhale. Though this process is involuntary, speech production involves a systematic outflow of air during exhalation characterized by linguistic content and prosodic factors of the utterance. Thus speech and respiration are closely related, and modeling this relationship makes sensing respiratory dynamics directly from the speech plausible, however is not well explored. In this article, we conduct a comprehensive study to explore techniques for sensing breathing signal and breathing parameters from speech using deep learning architectures and address the challenges involved in establishing the practical purpose of this technology. Estimating the breathing pattern from the speech would give us information about the respiratory parameters, thus enabling us to understand the respiratory health using one’s speech.}