Virtual autoencoder based recommendation system for individualizing head-related transfer functions

Luo, Yuhua; Zotkin, Dmitry N.; Duraiswami, Ramani

doi:10.1109/waspaa.2013.6701816

Cited by 16 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This last set of experiments is based on the notion that autoencoders perform a similar task as PCA, while also learning non-linear feature spaces [16]. Accordingly we found that, with as little as 20 principal components, it is possible to reconstruct HRTFs with an average SD of 1.7 dB -see Fig.…”

Section: Pca-based Hrtf Predictionmentioning

confidence: 69%

HRTF Individualization using Deep Learning

Miccini

Spagnol

2020

2020 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)

View full text Add to dashboard Cite

The research presented in this paper focuses on Head-Related Transfer Function (HRTF) individualization using deep learning techniques. HRTF individualization is paramount for accurate binaural rendering, which is used in XR technologies, tools for the visually impaired, and many other applications. The rising availability of public HRTF data currently allows experimentation with different input data formats and various computational models. Accordingly, three research directions are investigated here: (1) extraction of predictors from user data; (2) unsupervised learning of HRTFs based on autoencoder networks; and (3) synthesis of HRTFs from anthropometric data using deep multilayer perceptrons and principal component analysis. While none of the aforementioned investigations has shown outstanding results to date, the knowledge acquired throughout the development and troubleshooting phases highlights areas of improvement which are expected to pave the way to more accurate models for HRTF individualization.

show abstract

Section: Pca-based Hrtf Predictionmentioning

confidence: 69%

HRTF Individualization using Deep Learning

Miccini

Spagnol

2020

2020 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)

View full text Add to dashboard Cite

show abstract

“…Many different algorithms have been developed for binaural sound localization including simple regression models like SVR [14], GPR [28], and deep neural network models [46]. In this paper, we follow a state-of-the art neural network-based model in [46], to evaluate the benefits of accurate HRTF predictions.…”

Section: Binaural Localizationmentioning

confidence: 99%

Individualizing Head-Related Transfer Functions for Binaural Acoustic Applications

Zandi¹,

El-Mohandes²,

Zheng³

2022

Preprint

View full text Add to dashboard Cite

A Head Related Transfer Function (HRTF) characterizes how a human ear receives sounds from a point in space, and depends on the shapes of one's head, pinna, and torso. Accurate estimations of HRTFs for human subjects are crucial in enabling binaural acoustic applications such as sound localization and 3D sound spatialization. Unfortunately, conventional approaches for HRTF estimation rely on specialized devices or lengthy measurement processes. This work proposes a novel lightweight method for HRTF individualization that can be implemented using commercial-off-the-shelf components and performed by average users in home settings. The proposed method has two key components: a generative neural network model that can be individualized to predict HRTFs of new subjects from sparse measurements, and a lightweight measurement procedure that collects HRTF data from spatial locations. Extensive experiments using a public dataset and in house measurement data from 10 subjects of different ages and genders, show that the individualized models significantly outperform a baseline model in the accuracy of predicted HRTFs. To further demonstrate the advantages of individualized HRTFs, we implement two prototype applications for binaural localization and acoustic spatialization. We find that the performance of a localization model is improved by 15 • after trained with individualized HRTFs. Furthermore, in hearing tests, the success rate of correctly identifying the azimuth direction of incoming sounds increases by 183% after individualization.

show abstract

“…Several individualization methods involving DL technologies have also been proposed. Luo et al [17] trained a stacked denoising autoencoder to encode and reconstruct HRTFs from multiple subjects. The resulting latent representation is then manipulated using feedback from the user to optimize their localization performances.…”

Section: Related Workmentioning

confidence: 99%

A hybrid approach to structural modeling of individualized HRTFs

Miccini

Spagnol

2021

2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)

View full text Add to dashboard Cite

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.

show abstract

Virtual autoencoder based recommendation system for individualizing head-related transfer functions

Cited by 16 publications

References 9 publications

HRTF Individualization using Deep Learning

HRTF Individualization using Deep Learning

Individualizing Head-Related Transfer Functions for Binaural Acoustic Applications

A hybrid approach to structural modeling of individualized HRTFs

Contact Info

Product

Resources

About