Lightweight Deep Learning Model for Assessment of Substitution Voicing and Speech after Laryngeal Carcinoma Surgery

SIMPLE SUMMARY: A total laryngectomy involves the full and permanent separation of the upper and lower airways, resulting in the loss of voice and inability to interact vocally. To identify, extract, and evaluate replacement voicing following laryngeal oncosurgery, we propose employing convolutional neural networks for categorization of speech representations (spectrograms). With an overall accuracy of 89.47 percent, our technique has the greatest true-positive rate of any of the tested state-of-the-art methodologies. ABSTRACT: Laryngeal carcinoma is the most common malignant tumor of the upper respiratory tract. Total laryngectomy provides complete and permanent detachment of the upper and lower airways that causes the loss of voice, leading to a patient’s inability to verbally communicate in the postoperative period. This paper aims to exploit modern areas of deep learning research to objectively classify, extract and measure the substitution voicing after laryngeal oncosurgery from the audio signal. We propose using well-known convolutional neural networks (CNNs) applied for image classification for the analysis of voice audio signal. Our approach takes an input of Mel-frequency spectrogram (MFCC) as an input of deep neural network architecture. A database of digital speech recordings of 367 male subjects (279 normal speech samples and 88 pathological speech samples) was used. Our approach has shown the best true-positive rate of any of the compared state-of-the-art approaches, achieving an overall accuracy of 89.47%.