TY - GEN
T1 - Exploring redundancy of HRTFs for fast training DNN-based HRTF personalization
AU - Chen, Tzu Yu
AU - Hsiao, Po Wen
AU - Chi, Tai-Shih
N1 - Publisher Copyright:
© 2018 APSIPA organization.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - A deep neural network (DNN) is constructed to predict the magnitude responses of the head-related transfer functions (HRTFs) of users for a specific direction and a specific ear. Using the CIPIC HRTF database (including 25 azimuth angles and 50 elevation angles for both ears), we trained 2500 DNNs to predict magnitude responses of all HRTFs of a user. To reduce training time, we propose to use the final weights of the trained DNN of a nearby direction as the initial weights of the current DNN under training since magnitude responses of the HRTFs are smoothly changing across nearby directions. Analysis of variance (ANOVA) was performed to show that the proposed training scheme produces equivalent magnitude responses of HRTFs as the standard training scheme with random initial weights in terms of the log-spectral distortion (LSD) measure. Meanwhile, the proposed training scheme can dramatically reduce training time by more than 95%.
AB - A deep neural network (DNN) is constructed to predict the magnitude responses of the head-related transfer functions (HRTFs) of users for a specific direction and a specific ear. Using the CIPIC HRTF database (including 25 azimuth angles and 50 elevation angles for both ears), we trained 2500 DNNs to predict magnitude responses of all HRTFs of a user. To reduce training time, we propose to use the final weights of the trained DNN of a nearby direction as the initial weights of the current DNN under training since magnitude responses of the HRTFs are smoothly changing across nearby directions. Analysis of variance (ANOVA) was performed to show that the proposed training scheme produces equivalent magnitude responses of HRTFs as the standard training scheme with random initial weights in terms of the log-spectral distortion (LSD) measure. Meanwhile, the proposed training scheme can dramatically reduce training time by more than 95%.
UR - http://www.scopus.com/inward/record.url?scp=85063533712&partnerID=8YFLogxK
U2 - 10.23919/APSIPA.2018.8659704
DO - 10.23919/APSIPA.2018.8659704
M3 - Conference contribution
AN - SCOPUS:85063533712
T3 - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
SP - 1929
EP - 1933
BT - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018
Y2 - 12 November 2018 through 15 November 2018
ER -