Parameterization of Sequence of MFCCs for DNN-based voice disorder detection
This work addresses voice disorder detection for medical diagnosis, but it is incremental as it builds on existing DNN methods with minor improvements.
The paper presents a DNN-based system for detecting three common voice disorders from audio recordings, achieving a score of 77.44 in a challenge, which was the second-best result before final submission.
In this article a DNN-based system for detection of three common voice disorders (vocal nodules, polyps and cysts; laryngeal neoplasm; unilateral vocal paralysis) is presented. The input to the algorithm is (at least 3-second long) audio recording of sustained vowel sound /a:/. The algorithm was developed as part of the "2018 FEMH Voice Data Challenge" organized by Far Eastern Memorial Hospital and obtained score value (defined in the challenge specification) of 77.44. This was the second best result before final submission. Final challenge results are not yet known during writing of this document. The document also reports changes that were made for the final submission which improved the score value in cross-validation by 0.6% points.