Reduced representations of HRTF datasets: A discriminant analysis approach

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper discusses reduced representations of HRTF datasets, fully descriptive of one's personalized properties. The data reduction is achieved through elimination of the least discriminative binaural-filter pairs from a set. For this purpose Linear Discriminant Analysis (LDA) was applied on the Music and Audio Research Laboratory (MARL) database of repeated HRTF measurements, which resulted in 67% data reduction. The effectiveness of the sparse HRTF mapping is assessed by way of the performance of a database matching system, followed by a subjective evaluation study. The results indicate that participants have demonstrated strong preference towards the selected HRTF sets, in contrast to the generic KEMAR set and the least similar selections from the repository.

Original languageEnglish (US)
Title of host publication135th Audio Engineering Society Convention 2013
PublisherAudio Engineering Society
Pages675-684
Number of pages10
StatePublished - 2013
Event135th Audio Engineering Society Convention 2013 - New York, NY, United States
Duration: Oct 17 2013Oct 20 2013

Other

Other135th Audio Engineering Society Convention 2013
CountryUnited States
CityNew York, NY
Period10/17/1310/20/13

Fingerprint

data reduction
music
elimination
filters
evaluation

ASJC Scopus subject areas

  • Acoustics and Ultrasonics

Cite this

Andreopoulou, A., Roginska, A., & Bello, J. P. (2013). Reduced representations of HRTF datasets: A discriminant analysis approach. In 135th Audio Engineering Society Convention 2013 (pp. 675-684). Audio Engineering Society.

Reduced representations of HRTF datasets : A discriminant analysis approach. / Andreopoulou, Areti; Roginska, Agnieszka; Bello, Juan Pablo.

135th Audio Engineering Society Convention 2013. Audio Engineering Society, 2013. p. 675-684.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Andreopoulou, A, Roginska, A & Bello, JP 2013, Reduced representations of HRTF datasets: A discriminant analysis approach. in 135th Audio Engineering Society Convention 2013. Audio Engineering Society, pp. 675-684, 135th Audio Engineering Society Convention 2013, New York, NY, United States, 10/17/13.
Andreopoulou A, Roginska A, Bello JP. Reduced representations of HRTF datasets: A discriminant analysis approach. In 135th Audio Engineering Society Convention 2013. Audio Engineering Society. 2013. p. 675-684
Andreopoulou, Areti ; Roginska, Agnieszka ; Bello, Juan Pablo. / Reduced representations of HRTF datasets : A discriminant analysis approach. 135th Audio Engineering Society Convention 2013. Audio Engineering Society, 2013. pp. 675-684
@inproceedings{e07cad7b942044f4a7c2c9dee92e890c,
title = "Reduced representations of HRTF datasets: A discriminant analysis approach",
abstract = "This paper discusses reduced representations of HRTF datasets, fully descriptive of one's personalized properties. The data reduction is achieved through elimination of the least discriminative binaural-filter pairs from a set. For this purpose Linear Discriminant Analysis (LDA) was applied on the Music and Audio Research Laboratory (MARL) database of repeated HRTF measurements, which resulted in 67{\%} data reduction. The effectiveness of the sparse HRTF mapping is assessed by way of the performance of a database matching system, followed by a subjective evaluation study. The results indicate that participants have demonstrated strong preference towards the selected HRTF sets, in contrast to the generic KEMAR set and the least similar selections from the repository.",
author = "Areti Andreopoulou and Agnieszka Roginska and Bello, {Juan Pablo}",
year = "2013",
language = "English (US)",
pages = "675--684",
booktitle = "135th Audio Engineering Society Convention 2013",
publisher = "Audio Engineering Society",
address = "United States",

}

TY - GEN

T1 - Reduced representations of HRTF datasets

T2 - A discriminant analysis approach

AU - Andreopoulou, Areti

AU - Roginska, Agnieszka

AU - Bello, Juan Pablo

PY - 2013

Y1 - 2013

N2 - This paper discusses reduced representations of HRTF datasets, fully descriptive of one's personalized properties. The data reduction is achieved through elimination of the least discriminative binaural-filter pairs from a set. For this purpose Linear Discriminant Analysis (LDA) was applied on the Music and Audio Research Laboratory (MARL) database of repeated HRTF measurements, which resulted in 67% data reduction. The effectiveness of the sparse HRTF mapping is assessed by way of the performance of a database matching system, followed by a subjective evaluation study. The results indicate that participants have demonstrated strong preference towards the selected HRTF sets, in contrast to the generic KEMAR set and the least similar selections from the repository.

AB - This paper discusses reduced representations of HRTF datasets, fully descriptive of one's personalized properties. The data reduction is achieved through elimination of the least discriminative binaural-filter pairs from a set. For this purpose Linear Discriminant Analysis (LDA) was applied on the Music and Audio Research Laboratory (MARL) database of repeated HRTF measurements, which resulted in 67% data reduction. The effectiveness of the sparse HRTF mapping is assessed by way of the performance of a database matching system, followed by a subjective evaluation study. The results indicate that participants have demonstrated strong preference towards the selected HRTF sets, in contrast to the generic KEMAR set and the least similar selections from the repository.

UR - http://www.scopus.com/inward/record.url?scp=84896457378&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896457378&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84896457378

SP - 675

EP - 684

BT - 135th Audio Engineering Society Convention 2013

PB - Audio Engineering Society

ER -