HRTF magnitude synthesis via sparse representation of anthropometric features

Biliński, Piotr; Ahrens, Jens; Thomas, Mark R.; Tashev, Ivan; Platt, John

doi:10.1109/icassp.2014.6854447

Cited by 51 publications

(29 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to design it properly, the knowledge of subjective perception should be considered. Since log-magnitude spectra preserves all of the perceptuallyrelevant information which is contained in a measured HRTF for a position [21], we design loss function derived from log-spectral distortion (LSD) which represents the difference between HRTFs on a logarithmic basis from human hearing, and has been widely used for objective evaluation of HRTFs models [25][26] [27]. LSD expresses the distortion between the estimated and the measured HRTFs.…”

Section: Universal Model Trainingmentioning

confidence: 99%

Parameter-Transfer Learning for Low-Resource Individualization of Head-Related Transfer Functions

Wang

2019

Interspeech 2019

View full text Add to dashboard Cite

Individualized head-related transfer functions (HRTFs) play an important role in accurate localization perception. However, it is a great challenge to efficiently measure continuous HRTFs for each person in full space. In this paper, we propose a parameter-transfer learning method termed PTL to obtain individualized HRTFs based on a small set of HRTF measurements. The key idea behind PTL is to transfer a HRTF generation model from other database to a target individual. To this end, PTL first pretrains a deep neural network (DNN)based universal model on a large database of HRTFs with the assist of domain knowledge. Domain knowledge is used to generate the input features derived from the solution to sound wave propagation equation at the physical level, and to design the loss function based on the knowledge of objective evaluation criterion. Then, the universal model is transferred to a target individual by adapting the parameters of a hidden layer of DNN with a small set of HRTF measurements. The adaptation layer is determined by experimental verification. We also conduct the objective and subjective experiments, and the results show that the proposed method outperforms the state-of-the-arts methods in terms of LSD and localization accuracy.

show abstract

Section: Universal Model Trainingmentioning

confidence: 99%

Parameter-Transfer Learning for Low-Resource Individualization of Head-Related Transfer Functions

Wang

2019

Interspeech 2019

View full text Add to dashboard Cite

show abstract

“…year # subjects # meas. # pairs ARI˚ [23] 2010 135 1150 138000 CIPIC [24] 2001 45 1250 56250 ITA˚˚ [25] 2016 46 2304 110592 Microsoft [9] 2015 252 400 100800 RIEC [26] 2014 105 865 90825…”

Section: Classification Performancementioning

confidence: 99%

“…They show that in a localization test, the model demonstrated qualitatively similar performance to a human subject. A related area of active research aims to personalize generic HRTFs given a user's anthropometric features [9,10,11].…”

Section: Introductionmentioning

confidence: 99%

Spatial Audio Feature Discovery with Convolutional Neural Networks

Thuillier

Gamper

Tashev

2018

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

The advent of mixed reality consumer products brings about a pressing need to develop and improve spatial sound rendering techniques for a broad user base. Despite a large body of prior work, the precise nature and importance of various sound localization cues and how they should be personalized for an individual user to improve localization performance is still an open research problem. Here we propose training a convolutional neural network (CNN) to classify the elevation angle of spatially rendered sounds and employing Layerwise Relevance Propagation (LRP) on the trained CNN model. LRP provides saliency maps that can be used to identify spectral features used by the network for classification. These maps, in addition to the convolution filters learned by the CNN, are discussed in the context of listening tests reported in the literature. The proposed approach could potentially provide an avenue for future studies on modeling and personalization of head-related transfer functions (HRTFs).

show abstract

“…Hu et al [11] conducted a nonlinear mapping from eight independent anthropometric features to the twelve weight vectors of the principal components by using back-propagation neural network to obtain individualized HRTFs. Under the assumption that the linear weighting relationship between HRTF magnitudes are the same for different subjects and anthropometric features, Bilinski et al [12] proposed the sparse efficient vectors, which can be used to represent anthropometric features of target subject with that of available subjects in the database. The individualized HRTF magnitudes could be obtained by multiplying the sparse vectors to the HRTF magnitudes in the database.…”

Section: Introductionmentioning

confidence: 99%

Advancement of Individualized Head-Related Transfer Functions (HRTFs) in Perceiving the Spatialization Cues: Case Study for an Integrated HRTF Individualization Method

Wang

Zeng

2019

Applied Sciences

View full text Add to dashboard Cite

Head-related transfer function (HRTF), which varies across individuals at the same direction, has grabbed widespread attention in the field of acoustics and been used in many scenarios. In order to in-depth investigate the performance of individualized HRTFs on perceiving the spatialization cues, this study presents an integrated algorithm to obtain individualized HRTFs, and explores the advancement of such individualized HRTFs in perceiving the spatialization cues through two different binaural experiments. An integrated method for HRTF individualization on the use of Principle Component Analysis (PCA), Multiple Linear Regression (MLR) and Partial Least Square Regression (PLSR) was presented first. The objective evaluation was then made to verify the algorithmic effectiveness of that method. Next, two subjective experiments were conducted to explore the advancement of individualized HRTFs in perceiving the spatialization cues. One was auditory directional discrimination degree based on semantic differential method, in which the azimuth information of sound sources was told to the listeners before listening. The other was auditory localization, in which the azimuth information was not told to the listeners before listening. The corresponding statistical analyses for the subjective experimental results were made. All the experimental results support that individualized HRTFs obtained from the presented method achieve a preferable performance in perceiving the spatialization cues.

show abstract

HRTF magnitude synthesis via sparse representation of anthropometric features

Cited by 51 publications

References 18 publications

Parameter-Transfer Learning for Low-Resource Individualization of Head-Related Transfer Functions

Parameter-Transfer Learning for Low-Resource Individualization of Head-Related Transfer Functions

Spatial Audio Feature Discovery with Convolutional Neural Networks

Advancement of Individualized Head-Related Transfer Functions (HRTFs) in Perceiving the Spatialization Cues: Case Study for an Integrated HRTF Individualization Method

Contact Info

Product

Resources

About