@article {13963, title = {Computation of the head-related transfer function via the fast multipole accelerated boundary element method and its spherical harmonic representation}, journal = {The Journal of the Acoustical Society of America}, volume = {127}, year = {2010}, month = {2010///}, pages = {370 - 386}, abstract = {The head-related transfer function (HRTF) is computed using the fast multipole accelerated boundary element method. For efficiency, the HRTF is computed using the reciprocity principle by placing a source at the ear and computing its field. Analysis is presented to modify the boundary value problem accordingly. To compute the HRTF corresponding to different ranges via a single computation, a compact and accurate representation of the HRTF, termed the spherical spectrum, is developed. Computations are reduced to a two stage process, the computation of the spherical spectrum and a subsequent evaluation of the HRTF. This representation allows easy interpolation and range extrapolation of HRTFs. HRTF computations are performed for the range of audible frequencies up to 20 kHz for several models including a sphere, human head models [the Neumann KU-100 ({\textquotedblleft}Fritz{\textquotedblright}) and the Knowles KEMAR ({\textquotedblleft}Kemar{\textquotedblright}) manikins], and head-and-torso model (the Kemar manikin). Comparisons between the different cases are provided. Comparisons with the computational data of other authors and available experimental data are conducted and show satisfactory agreement for the frequencies for which reliable experimental data are available. Results show that, given a good mesh, it is feasible to compute the HRTF over the full audible range on a regular personal computer.}, keywords = {auditory evoked potentials, bioacoustics, boundary-elements methods, Ear, Harmonic analysis}, doi = {10.1121/1.3257598}, url = {http://link.aip.org/link/?JAS/127/370/1}, author = {Gumerov, Nail A. and O{\textquoteright}Donovan,Adam E. and Duraiswami, Ramani and Zotkin,Dmitry N} } @conference {18467, title = {Regularized HRTF fitting using spherical harmonics}, booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2009. WASPAA {\textquoteright}09}, year = {2009}, month = {2009/10//}, pages = {257 - 260}, publisher = {IEEE}, organization = {IEEE}, abstract = {By the Helmholtz reciprocity principle, the head-related transfer function (HRTF) is equivalent to an acoustic field created by a transmitter placed at the ear location. Therefore, it can be represented as a spherical harmonics spectrum - a weighted sum of spherical harmonics. Such representations are useful in theoretical and computational analysis. Many different (often severely undersampled) grids are used for HRTF measurement, making the spectral reconstruction difficult. In this paper, two methods of obtaining the spectrum are presented and analyzed both on synthetic (ground-truth data available) and real HRTF measurements.}, keywords = {Acoustic applications, acoustic field, Acoustic fields, acoustic intensity measurement, Acoustic measurements, acoustic signal processing, Acoustic testing, acoustic waves, array signal processing, audio acoustics, circular arrays, computational analysis, Ear, ear location, head-related transfer function, Helmholtz reciprocity principle, HRTF, HRTF fitting, Loudspeakers, Microphones, Position measurement, signal reconstruction, spatial audio, spectral reconstruction, spherical harmonics, Transfer functions}, isbn = {978-1-4244-3678-1}, doi = {10.1109/ASPAA.2009.5346521}, author = {Zotkin,Dmitry N and Duraiswami, Ramani and Gumerov, Nail A.} } @conference {14516, title = {Efficient Conversion of X.Y Surround Sound Content to Binaural Head-Tracked Form for HRTF-Enabled Playback}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, 2007. ICASSP 2007}, volume = {1}, year = {2007}, month = {2007/04//}, pages = {I-21-I-24 - I-21-I-24}, publisher = {IEEE}, organization = {IEEE}, abstract = {Binaural presentation of X.Y sound is usually performed using virtual audio principles - that is, by attempting to virtually reproduce the setup of the X+Y loudspeakers in the reference room configuration. The computational cost of such playback is linear in the number of channels in the X.Y setup. We present a novel scheme that computes, offline, a spatio-temporal representation of the sound field in the listening area and store it as a multipole expansion. During head-tracked playback, the binaural signal is obtained by evaluating the multipole expansion at the ear position corresponding to the current user pose, resulting in a fixed playback cost. The representation is further extended to incorporate individualized HRTFs at no additional cost. Simulation results are presented.}, keywords = {Acoustic fields, Acoustic scattering, acoustic signal processing, audio acoustics, Audio systems, binaural head-tracked, binaural presentation, Computational efficiency, Costs, Ear, head-related transfer function, Headphones, HRTF-enabled playback, Loudspeakers, Music, reverberation, sound field, spatio-temporal representation, surround sound, surround sound content, Transfer functions, virtual audio principles}, isbn = {1-4244-0727-3}, doi = {10.1109/ICASSP.2007.366606}, author = {Zotkin,Dmitry N and Duraiswami, Ramani and Gumerov, Nail A.} } @conference {18458, title = {Fast Multipole Accelerated Boundary Elements for Numerical Computation of the Head Related Transfer Function}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, 2007. ICASSP 2007}, volume = {1}, year = {2007}, month = {2007/04//}, pages = {I-165-I-168 - I-165-I-168}, publisher = {IEEE}, organization = {IEEE}, abstract = {The numerical computation of head related transfer functions has been attempted by a number of researchers. However, the cost of the computations has meant that usually only low frequencies can be computed and further the computations take inordinately long times. Because of this, comparisons of the computations with measurements are also difficult. We present a fast multipole based iterative preconditioned Krylov solution of a boundary element formulation of the problem and use a new formulation that enables the reciprocity technique to be accurately employed. This allows the calculation to proceed for higher frequencies and larger discretizations. Preliminary results of the computations and of comparisons with measured HRTFs are presented.}, keywords = {Acceleration, Acoustic measurements, Acoustic scattering, audio signal processing, boundary element formulation, Boundary element method, Boundary element methods, boundary-elements methods, Costs, Ear, Fast Multipole Method, Frequency, Head related transfer function, HUMANS, Irrigation, iterative methods, multipole accelerated boundary elements, multipole based iterative preconditioned Krylov solution, numerical computation, Reciprocity, Transfer functions}, isbn = {1-4244-0727-3}, doi = {10.1109/ICASSP.2007.366642}, author = {Gumerov, Nail A. and Duraiswami, Ramani and Zotkin,Dmitry N} } @conference {13849, title = {Reranking for Sentence Boundary Detection in Conversational Speech}, booktitle = {2006 IEEE International Conference on Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings}, volume = {1}, year = {2006}, month = {2006/05/14/19}, pages = {I-I - I-I}, publisher = {IEEE}, organization = {IEEE}, abstract = {We present a reranking approach to sentence-like unit (SU) boundary detection, one of the EARS metadata extraction tasks. Techniques for generating relatively small n-best lists with high oracle accuracy are presented. For each candidate, features are derived from a range of information sources, including the output of a number of parsers. Our approach yields significant improvements over the best performing system from the NIST RT-04F community evaluation}, keywords = {Automatic speech recognition, conversational speech, data mining, Ear, EARS metadata extraction tasks, Feature extraction, hidden Markov models, meta data, Model driven engineering, NIST, NIST RT-04F community evaluation, oracle accuracy, performance evaluation, reranking, sentence-like unit boundary detection, Speech processing, Speech recognition, Telephony}, isbn = {1-4244-0469-X}, doi = {10.1109/ICASSP.2006.1660078}, author = {Roark,B. and Liu,Yang and Harper,M. and Stewart,R. and Lease,M. and Snover,M. and Shafran,I. and Dorr, Bonnie J and Hale,J. and Krasnyanskaya,A. and Yung,L.} } @article {14028, title = {Extracting the frequencies of the pinna spectral notches in measured head related impulse responses}, journal = {The Journal of the Acoustical Society of America}, volume = {118}, year = {2005}, month = {2005///}, pages = {364 - 374}, abstract = {The head related impulse response (HRIR) characterizes the auditory cues created by scattering of sound off a person{\textquoteright}s anatomy. The experimentally measured HRIR depends on several factors such as reflections from body parts (torso, shoulder, and knees), head diffraction, and reflection/diffraction effects due to the pinna. Structural models (Algazi et al., 2002; Brown and Duda, 1998) seek to establish direct relationships between the features in the HRIR and the anatomy. While there is evidence that particular features in the HRIR can be explained by anthropometry, the creation of such models from experimental data is hampered by the fact that the extraction of the features in the HRIR is not automatic. One of the prominent features observed in the HRIR, and one that has been shown to be important for elevation perception, are the deep spectral notches attributed to the pinna. In this paper we propose a method to robustly extract the frequencies of the pinna spectral notches from the measured HRIR, distinguishing them from other confounding features. The method also extracts the resonances described by Shaw (1997). The techniques are applied to the publicly available CIPIC HRIR database (Algazi et al., 2001c). The extracted notch frequencies are related to the physical dimensions and shape of the pinna.}, keywords = {acoustic wave reflection, acoustic wave scattering, anthropometry, Ear, hearing, physiological models}, doi = {10.1121/1.1923368}, url = {http://link.aip.org/link/?JAS/118/364/1}, author = {Raykar,Vikas C. and Duraiswami, Ramani and Yegnanarayana,B.} } @conference {13236, title = {HRTF personalization using anthropometric measurements}, booktitle = {Applications of Signal Processing to Audio and Acoustics, 2003 IEEE Workshop on.}, year = {2003}, month = {2003/10//}, pages = {157 - 160}, abstract = {Individualized head related transfer functions (HRTFs) are needed for accurate rendering of spatial audio, which is important in many applications. Since these are relatively tedious to acquire, they may not be acceptable for some applications. A number of studies have sought to perform simple customization of the HRTF. We propose and test a strategy for HRTF personalization, based on matching certain anthropometric ear parameters with the HRTF database, and the incorporation of a low-frequency "head-and-torso" model. We present preliminary tests aimed at evaluation of this customization. Results show that the approach improves both the accuracy of the localization and subjective perception of the virtual auditory scene.}, keywords = {acoustic, anthropometric, audio, audio;, auditory, Ear, functions;, Head, head-and-torso, HRTF, individualized, localization;, measurements;, model;, models;, parameters;, perception;, personalization;, physiological, processing;, related, scattering;, scene;, signal, sound, spatial, subjective, transfer, virtual, wave}, doi = {10.1109/ASPAA.2003.1285855}, author = {Zotkin,Dmitry N and Hwang,J. and Duraiswami, Ramani and Davis, Larry S.} } @conference {18470, title = {Virtual audio system customization using visual matching of ear parameters}, booktitle = {16th International Conference on Pattern Recognition, 2002. Proceedings}, volume = {3}, year = {2002}, month = {2002///}, pages = {1003- 1006 vol.3 - 1003- 1006 vol.3}, publisher = {IEEE}, organization = {IEEE}, abstract = {Applications in the creation of virtual auditory spaces (VAS) and sonification require individualized head related transfer functions (HRTFs) for perceptual fidelity. HRTFs exhibit significant variation from person to person due to differences between their pinnae, and their body sizes. We propose and preliminarily implement a simple HRTF customization based on the use of a published database of HRTFs (Algazi et al., 2001) that also contains geometrical measurements of subject pinnae. We measure some of these features via simple image processing, and select the HRTF that has features most closely corresponding to the individual{\textquoteright}s features. This selection procedure is implemented along with the virtual auditory system described in (Zotkin et al., 2002), and listener tests conducted comparing the customized HRTF and a fixed HRTF. Despite the simplicity of the method, tests reveal average improvement in localization accuracy of about 25 percent, though performance improvement varies with source location and individuals.}, keywords = {acoustic signal processing, Audio systems, Auditory system, Computer vision, database, Ear, ear parameter matching, geometrical measurements, Head, head related transfer functions, HRTF customization, Image databases, IMAGE PROCESSING, medical image processing, performance improvement, Position measurement, sonification, Spatial databases, System testing, Transfer functions, virtual audio system customization, virtual auditory spaces, virtual auditory system, visual matching}, isbn = {0-7695-1695-X}, doi = {10.1109/ICPR.2002.1048207}, author = {Zotkin,Dmitry N and Duraiswami, Ramani and Davis, Larry S. and Mohan,A. and Raykar,V.} } @conference {14529, title = {Modeling the effect of a nearby boundary on the HRTF}, booktitle = {2001 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP {\textquoteright}01)}, volume = {5}, year = {2001}, month = {2001///}, pages = {3337-3340 vol.5 - 3337-3340 vol.5}, publisher = {IEEE}, organization = {IEEE}, abstract = {Understanding and simplified modeling of the head related transfer function (HRTF) holds the key to many applications in spatial audio. We develop an analytical solution to the problem of scattering of sound from a sphere in the vicinity of an infinite plane. Using this solution we study the influence of a nearby scattering rigid surface, on a spherical model for the HRTF}, keywords = {Acoustic scattering, acoustic signal processing, acoustic wave reflection, acoustic wave scattering, architectural acoustics, audio signal processing, Biological system modeling, boundary effect modeling, Computer interfaces, Ear, Educational institutions, Frequency, Head related transfer function, HRTF, HUMANS, infinite plane, Laboratories, Nails, Raman scattering, rigid surface, room environment, sound pressure level, sound scattering, spatial audio, sphere, spherical model, Transfer functions, wall influence}, isbn = {0-7803-7041-4}, doi = {10.1109/ICASSP.2001.940373}, author = {Gumerov, Nail A. and Duraiswami, Ramani} } @conference {14576, title = {A distributed algorithm for ear decomposition}, booktitle = {, Fifth International Conference on Computing and Information, 1993. Proceedings ICCI {\textquoteright}93}, year = {1993}, month = {1993/05/27/29}, pages = {180 - 184}, publisher = {IEEE}, organization = {IEEE}, abstract = {A distributed algorithm for finding an ear decomposition of an asynchronous communication network with n nodes and m links is presented. At the completion of the algorithm either the ears are correctly labeled or the nodes are informed that there exists no ear decomposition. First we present a novel algorithm to check the existence of an ear decomposition which uses O(m) messages. We also present two other algorithms, one which is time-optimal and the other which is message-optimal to determine the actual ears and their corresponding numbers after determining the existence of an ear decomposition}, keywords = {Asynchronous communication, asynchronous communication network, Automata, Communication networks, computational complexity, Computer networks, Computer science, decomposition graph, distributed algorithm, distributed algorithms, Distributed computing, Ear, ear decomposition, graph theory, message-optimal, network decomposition, sorting, Testing, time-optimal}, isbn = {0-8186-4212-2}, doi = {10.1109/ICCI.1993.315382}, author = {Hannenhalli, Sridhar and Perumalla,K. and Chandrasekharan,N. and Sridhar,R.} }