Whispered Hearing Analyzer — a device for preventive examinations to detect early hearing loss

Introduction. The problem of hearing loss and deafness, due to the general prevalence of hearing loss in different age groups, is significant not only for medicine, but also for the social sphere of society. Nowadays, just as 40 years ago, preventive medical examinations and initial examinations by an otorhinolaryngologist use methods of testing hearing by means of whispered speech, which has its own characteristics for everyone. This leads to diagnostic errors and does not allow to detect hearing loss in its early stages. Purpose of the study—development of a whispered-speech apparatus for early express diagnosis of hearing loss, and study of the effectiveness of the developed apparatus. Materials and methods. The Department of Hygiene at the Izhevsk State Medical Academy, as part of the program "Umnic-2018" a whispered hearing analyzer — a device for early express diagnosis of hearing loss was developed. The device was tested on the basis of otorhinolaryngologist offices in Izhevsk and Tchaikovsky. The study group included 53 patients aged 19 to 76. As part of the testing of the device, the subjects underwent whispered speech hearing tests using acumetric Voyacek word tables; express diagnostics of the hearing level with the whispered hearing analyzer and tonal threshold audiometry using the ITERA II diagnostic audiometer (Otometrics, Denmark). Results. As a result of the testing of the developed device, we found that the use of the whispered hearing analyzer allows you to reduce the time of examination and increase its diagnostic efficiency compared to conventional methods of hearing level examination at medical check-ups. Discussion. The Whispering Hearing Analyzer is designed to quickly and accurately detect hearing loss during medical examinations. The results obtained with this instrument can only tell you that you have a hearing loss, but it is not possible to make a diagnosis. Conclusion. The problem of disabling hearing loss can be solved through preventive measures, one of which is the developed device for early express diagnosis of hearing loss. The use of this device eliminates the occurrence of diagnostic errors associated with the researcher's speech characteristics, thereby making it possible to detect hearing loss at an early stage.

Real-time synthesis of imagined speech processes from minimally invasive recordings of neural activity

Speech neuroprosthetics aim to provide a natural communication channel to individuals who are unable to speak due to physical or neurological impairments. Real-time synthesis of acoustic speech directly from measured neural activity could enable natural conversations and notably improve quality of life, particularly for individuals who have severely limited means of communication. Recent advances in decoding approaches have led to high quality reconstructions of acoustic speech from invasively measured neural activity. However, most prior research utilizes data collected during open-loop experiments of articulated speech, which might not directly translate to imagined speech processes. Here, we present an approach that synthesizes audible speech in real-time for both imagined and whispered speech conditions. Using a participant implanted with stereotactic depth electrodes, we were able to reliably generate audible speech in real-time. The decoding models rely predominately on frontal activity suggesting that speech processes have similar representations when vocalized, whispered, or imagined. While reconstructed audio is not yet intelligible, our real-time synthesis approach represents an essential step towards investigating how patients will learn to operate a closed-loop speech neuroprosthesis based on imagined speech.

Real-time Synthesis of Imagined Speech Processes from Minimally Invasive Recordings of Neural Activity

ABSTRACTSpeech neuroprosthetics aim to provide a natural communication channel to individuals who are unable to speak due to physical or neurological impairments. Real-time synthesis of acoustic speech directly from measured neural activity could enable natural conversations and significantly improve quality of life, particularly for individuals who have severely limited means of communication. Recent advances in decoding approaches have led to high quality reconstructions of acoustic speech from invasively measured neural activity. However, most prior research utilizes data collected during open-loop experiments of articulated speech, which neglects the critical human-in-the-loop aspect of a practical speech neuroprosthetic.Here we present an approach that synthesizes audible speech in real-time for both imagined and whispered speech conditions. Using a participant implanted with stereotactic depth electrodes, we were able to reliably generate audible speech in real-time. The decoding models rely predominately on frontal activity suggesting that speech processes have similar representations when vocalized, whispered, or imagined. Our real-time synthesis approach represents an essential step towards investigating how patients will learn to operate a closed-loop speech neuroprosthesis, as well as the development of techniques that incorporate co-adaptation of the user and system for optimized performance.