Abstract
(1) Background: The application of machine learning techniques in the speech recognition literature has become a large field of study. Here, we aim to (1) expand the available evidence for the use of machine learning techniques for voice classification and (2) discuss the implications of such approaches towards the development of novel hearing aid features (i.e., voice familiarity detection). To do this, we built and tested a Convolutional Neural Network (CNN) Model for the identification and classification of a series of voices, namely the 10 cast members of the popular television show “Modern Family”. (2) Methods: Representative voice samples were selected from Season 1 of Modern Family (N = 300; 30 samples for each of the classes of the classification in this model, namely Phil, Claire, Hailey, Alex, Luke, Gloria, Jay, Manny, Mitch, Cameron). The audio samples were then cleaned and normalized. Feature extraction was then implemented and used as the input to train a basic CNN model and an advanced CNN model. (3) Results: Accuracy of voice classification for the basic model was 89%. Accuracy of the voice classification for the advanced model was 99%. (4) Conclusions: Greater familiarity with a voice is known to be beneficial for speech recognition. If a hearing aid can eventually be programmed to recognize voices that are familiar or not, perhaps it can also apply familiar voice features to improve hearing performance. Here we discuss how such machine learning, when applied to voice recognition, is a potential technological solution in the coming years.
Highlights
There are many hearing aid features and advances that have been shown to improve outcomes for individuals with hearing loss
In the future, real time processing could be leveraged to enhance the features of a novel voice by applying the stored features of a familiar voice, it may be possible to leverage a non-hearing aid feature by taking advantage of the tiny computer(s) the patient has in their ears
After using our advanced machine learning model to train the data, we demonstrated that when using the advanced model, after 50 epochs of training, the testing accuracy of the Convolutional Neural Network (CNN) model is 99.95% (Figure 8A,B)
Summary
There are many hearing aid features and advances that have been shown to improve outcomes for individuals with hearing loss. They increase speech perception and comfort in background noise while decreasing the effort required to listen [1]. We propose a new potential feature, voice identification and conversion, to explore voice familiarity as a possible hearing aid feature as voice familiarity has been shown to have specific neural markers [23,24] and improve speech recognition in adults with [25,26] and without [27] hearing loss. We aim to (1) expand the available evidence for the use of machine learning techniques for voice classification and (2) discuss the implications of such approaches towards the development of novel hearing aid features (i.e., voice familiarity detection)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
