Print Email Facebook Twitter A hybrid approach to structural modeling of individualized HRTFs Title A hybrid approach to structural modeling of individualized HRTFs Author Miccini, Riccardo (Aalborg University) Spagnol, S. (TU Delft Design Aesthetics) Date 2021 Abstract We present a hybrid approach to individualized head-related transfer function (HRTF) modeling which requires only 3 anthropometric measurements and an image of the pinna. A prediction algorithm based on variational autoencoders synthesizes a pinna-related response from the image, which is used to filter a measured head-andtorso response. The interaural time difference is then manipulated to match that of the HUTUBS dataset subject minimizing the predicted localization error. The results are evaluated using spectral distortion and an auditory localization model. While the latter is inconclusive regarding the efficacy of the structural model, the former metric shows promising results with encoding HRTFs. Index Terms: Hardware - Digital signal processing; Computing methodologies - Neural networks; Applied computing - Sound and music computing Subject Digital signal processingNeural networksSound and music computing To reference this document use: http://resolver.tudelft.nl/uuid:37bad4b1-09ef-4386-bb56-5e52c18caa3a DOI https://doi.org/10.1109/VRW52623.2021.00022 Publisher IEEE, Piscataway, NJ, USA ISBN 978-0-7381-1367-8 Source Proceedings - 2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2021 Event 2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2021, 2021-03-27 → 2021-04-03, Virtual, Lisbon, Portugal Series Proceedings - 2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2021 Part of collection Institutional Repository Document type conference paper Rights © 2021 Riccardo Miccini, S. Spagnol Files PDF VRW_2021.pdf 1.39 MB Close viewer /islandora/object/uuid:37bad4b1-09ef-4386-bb56-5e52c18caa3a/datastream/OBJ/view