Validating a perceptual distraction model using a personal two-zone sound system

Jussi Rämö, Lasse Christensen, Søren Bech, Søren Holdt Jensen

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

This paper focuses on validating a perceptual distraction model, which aims to predict user's perceived distraction caused by audio-on-audio interference. Originally, the distraction model was trained with music targets and interferers using a simple loudspeaker setup, consisting of only two loudspeakers. Recently, the model was successfully validated in a complex personal sound-zone system with music targets and speech interferers. In this paper, a second round of validations were conducted by physically altering the sound-zone system and running listening experiments utilizing both of the two sound zones within the sound-zone system. Thus, validating the model using a different sound-zone system with both speech-on-music and music-on-speech stimuli sets. The results show that the model performance is equally good in both zones, i.e., with both speech- on-music and music-on-speech stimuli, and comparable to the previous validation round. The calculated root mean squared errors in Zone A and B were 11.3% and 10.4%, respectively, compared to the 11.0% from the previous validation round. The results further confirm that the distraction model can be used as a valuable tool in evaluating and optimizing the performance of personal sound-zone systems.
Original languageEnglish
Title of host publicationProceedings of Acoustics `17 Boston : 173rd Meeting of Acoustical Society of America and 8th Forum Acusticum
Number of pages12
PublisherAcoustical Society of America
Publication dateJul 2017
Pages1-12
Article number050003
DOIs
Publication statusPublished - Jul 2017
EventAcoustics '17 Boston: 173rd Meeting of Acoustical Society of America and 8th Forum Acusticum - Boston, United States
Duration: 25 Jun 201729 Jun 2017

Conference

ConferenceAcoustics '17 Boston
CountryUnited States
CityBoston
Period25/06/201729/06/2017
SeriesMeetings on Acoustics. Proceedings
Number1
Volume30
ISSN1939-800X

Fingerprint

Acoustic waves
Loudspeakers
Experiments

Keywords

  • Psychoacoustics
  • Predictive models
  • Sound zones
  • Acoustic signal processing
  • Audio systems

Cite this

Rämö, J., Christensen, L., Bech, S., & Jensen, S. H. (2017). Validating a perceptual distraction model using a personal two-zone sound system. In Proceedings of Acoustics `17 Boston: 173rd Meeting of Acoustical Society of America and 8th Forum Acusticum (pp. 1-12). [050003] Acoustical Society of America. Meetings on Acoustics. Proceedings, No. 1, Vol.. 30 https://doi.org/10.1121/2.0000534
Rämö, Jussi ; Christensen, Lasse ; Bech, Søren ; Jensen, Søren Holdt. / Validating a perceptual distraction model using a personal two-zone sound system. Proceedings of Acoustics `17 Boston: 173rd Meeting of Acoustical Society of America and 8th Forum Acusticum. Acoustical Society of America, 2017. pp. 1-12 (Meetings on Acoustics. Proceedings; No. 1, Vol. 30).
@inproceedings{4fdf71a8ac154358850fed9ca3f975bc,
title = "Validating a perceptual distraction model using a personal two-zone sound system",
abstract = "This paper focuses on validating a perceptual distraction model, which aims to predict user's perceived distraction caused by audio-on-audio interference. Originally, the distraction model was trained with music targets and interferers using a simple loudspeaker setup, consisting of only two loudspeakers. Recently, the model was successfully validated in a complex personal sound-zone system with music targets and speech interferers. In this paper, a second round of validations were conducted by physically altering the sound-zone system and running listening experiments utilizing both of the two sound zones within the sound-zone system. Thus, validating the model using a different sound-zone system with both speech-on-music and music-on-speech stimuli sets. The results show that the model performance is equally good in both zones, i.e., with both speech- on-music and music-on-speech stimuli, and comparable to the previous validation round. The calculated root mean squared errors in Zone A and B were 11.3{\%} and 10.4{\%}, respectively, compared to the 11.0{\%} from the previous validation round. The results further confirm that the distraction model can be used as a valuable tool in evaluating and optimizing the performance of personal sound-zone systems.",
keywords = "Psychoacoustics, Predictive models, Sound zones, Acoustic signal processing, Audio systems",
author = "Jussi R{\"a}m{\"o} and Lasse Christensen and S{\o}ren Bech and Jensen, {S{\o}ren Holdt}",
year = "2017",
month = "7",
doi = "10.1121/2.0000534",
language = "English",
series = "Meetings on Acoustics. Proceedings",
publisher = "Acoustical Society of America",
number = "1",
pages = "1--12",
booktitle = "Proceedings of Acoustics `17 Boston",

}

Rämö, J, Christensen, L, Bech, S & Jensen, SH 2017, Validating a perceptual distraction model using a personal two-zone sound system. in Proceedings of Acoustics `17 Boston: 173rd Meeting of Acoustical Society of America and 8th Forum Acusticum., 050003, Acoustical Society of America, Meetings on Acoustics. Proceedings, no. 1, vol. 30, pp. 1-12, Acoustics '17 Boston, Boston, United States, 25/06/2017. https://doi.org/10.1121/2.0000534

Validating a perceptual distraction model using a personal two-zone sound system. / Rämö, Jussi; Christensen, Lasse; Bech, Søren; Jensen, Søren Holdt.

Proceedings of Acoustics `17 Boston: 173rd Meeting of Acoustical Society of America and 8th Forum Acusticum. Acoustical Society of America, 2017. p. 1-12 050003 (Meetings on Acoustics. Proceedings; No. 1, Vol. 30).

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Validating a perceptual distraction model using a personal two-zone sound system

AU - Rämö, Jussi

AU - Christensen, Lasse

AU - Bech, Søren

AU - Jensen, Søren Holdt

PY - 2017/7

Y1 - 2017/7

N2 - This paper focuses on validating a perceptual distraction model, which aims to predict user's perceived distraction caused by audio-on-audio interference. Originally, the distraction model was trained with music targets and interferers using a simple loudspeaker setup, consisting of only two loudspeakers. Recently, the model was successfully validated in a complex personal sound-zone system with music targets and speech interferers. In this paper, a second round of validations were conducted by physically altering the sound-zone system and running listening experiments utilizing both of the two sound zones within the sound-zone system. Thus, validating the model using a different sound-zone system with both speech-on-music and music-on-speech stimuli sets. The results show that the model performance is equally good in both zones, i.e., with both speech- on-music and music-on-speech stimuli, and comparable to the previous validation round. The calculated root mean squared errors in Zone A and B were 11.3% and 10.4%, respectively, compared to the 11.0% from the previous validation round. The results further confirm that the distraction model can be used as a valuable tool in evaluating and optimizing the performance of personal sound-zone systems.

AB - This paper focuses on validating a perceptual distraction model, which aims to predict user's perceived distraction caused by audio-on-audio interference. Originally, the distraction model was trained with music targets and interferers using a simple loudspeaker setup, consisting of only two loudspeakers. Recently, the model was successfully validated in a complex personal sound-zone system with music targets and speech interferers. In this paper, a second round of validations were conducted by physically altering the sound-zone system and running listening experiments utilizing both of the two sound zones within the sound-zone system. Thus, validating the model using a different sound-zone system with both speech-on-music and music-on-speech stimuli sets. The results show that the model performance is equally good in both zones, i.e., with both speech- on-music and music-on-speech stimuli, and comparable to the previous validation round. The calculated root mean squared errors in Zone A and B were 11.3% and 10.4%, respectively, compared to the 11.0% from the previous validation round. The results further confirm that the distraction model can be used as a valuable tool in evaluating and optimizing the performance of personal sound-zone systems.

KW - Psychoacoustics

KW - Predictive models

KW - Sound zones

KW - Acoustic signal processing

KW - Audio systems

U2 - 10.1121/2.0000534

DO - 10.1121/2.0000534

M3 - Article in proceeding

T3 - Meetings on Acoustics. Proceedings

SP - 1

EP - 12

BT - Proceedings of Acoustics `17 Boston

PB - Acoustical Society of America

ER -

Rämö J, Christensen L, Bech S, Jensen SH. Validating a perceptual distraction model using a personal two-zone sound system. In Proceedings of Acoustics `17 Boston: 173rd Meeting of Acoustical Society of America and 8th Forum Acusticum. Acoustical Society of America. 2017. p. 1-12. 050003. (Meetings on Acoustics. Proceedings; No. 1, Vol. 30). https://doi.org/10.1121/2.0000534