On the Use of Bottleneck Features of CNN Auto-Encoder for Personalized HRTFs

Lee GW, Moon JM, Chun CJ, Kim HK. On the Use of Bottleneck Features of CNN Auto-Encoder for Personalized HRTFs. In: AES Convention 144. Audio Engineering Society; 2018. Paper 10023. Available from: https://aes.org/publications/elibrary-page/?id=19419

@inproceedings{Lee2018_19419,
  author = {Lee, Geon Woo and Moon, Jung Min and Chun, Chan Jun and Kim, Hong Kook},
  title = {{On the Use of Bottleneck Features of CNN Auto-Encoder for Personalized HRTFs}},
  booktitle = {AES Convention 144},
  note = {Paper 10023},
  year = {2018},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=19419}
}

TY  - CPAPER
TI  - On the Use of Bottleneck Features of CNN Auto-Encoder for Personalized HRTFs
AU  - Lee, Geon Woo
AU  - Moon, Jung Min
AU  - Chun, Chan Jun
AU  - Kim, Hong Kook
T2  - AES Convention 144
M1  - Paper 10023
PY  - 2018
DA  - 2018/05/06
UR  - https://aes.org/publications/elibrary-page/?id=19419
PB  - Audio Engineering Society
LA  - en
AB  - The most effective way of providing immersive sound effects is to use head-related transfer functions (HRTFs). HRTFs are defined by the path from a given sound source to the listener's ears. However, sound propagation by HRTFs differs slightly between people because the head, body, and ears differ for each person. Recently, a method for estimating HRTFs using a neural network has been developed, where anthropometric pinna measurements and head-related impulse responses (HRIRs) are used as the input and output layer of the neural network. However, it is inefficient to accurately measure such anthropometric data. This paper proposes a feature extraction method for the ear image instead of measuring anthropometric pinna measurements directly. The proposed method utilizes the bottleneck features of a convolutional neural network (CNN) auto-encoder from the edge detected ear image. The proposed feature extraction method using the CNN-based auto-encoder will be incorporated into the HRTF estimation approach.
ER  -