This paper describes a subjective assessment procedure and an objective prediction model for sound quality assessment of earphones. The proposed subjective assessment procedure is designed to provide an instantaneous switching from one stimulus to another or reference stimulus. Based on the result from subjective assessment, an objective prediction model was designed using Average Distorted Block (ADBB) [1]. Eight earphones were assessed by the proposed subjective assessment procedure. The perceived Mean Opinion Score (MOSs) were used in the regression process in ADBB. The result shows that the proposed objective prediction model achieves an outstanding performance with a cross correlation of 0.9 and root mean square error of 7.57 in a 100 point scale.
(See document for exact affiliation information.)
https://aes2.org/publications/elibrary-page/?id=15475
(2519KB)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
