Word Spotting in Background Music: a Behavioural Study

Letizia Marchegiani, Xenofon Fafoutis

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Resumé

Introduction Speech intelligibility in realistic environments is directly correlated with the ability of focusing attention on the sounds of interest while discarding the background noise and other competing stimuli. This work investigates task-driven auditory attention in noisy environments. Specifically, this study focuses on the ability to successfully execute a word spotting task while speech perception has to cope with the presence of music playing in the background. Methods The executed behavioural experiments consider different types of songs and explore how their distinct characteristics (such as dynamics or presence of distortion sound effects) affect the subjects’ task performance and, thus, the distribution of attention. Results Our results show that the ability of correctly separating the target sound from the background noise has a major impact on the performance of the subjects. Indeed, songs not presenting any distortion effect result in being more distracting than the ones with distortion, whose frequency spectrum envelop differentiates more from the one of the narrative. Furthermore, subjects performed the worst with songs characterised by high dynamics playing in the background, due to the unexpected changes capturing the attention of the listener.

OriginalsprogEngelsk
TidsskriftCognitive Computation
Vol/bind11
Udgave nummer5
Sider (fra-til)711–718
Antal sider8
ISSN1866-9964
DOI
StatusUdgivet - okt. 2019

Fingerprint

Metrorrhagia
Music
Aptitude
Acoustic waves
Acoustic noise
Speech intelligibility
Noise
Speech Intelligibility
Speech Perception
Task Performance and Analysis
Experiments

Citer dette

Marchegiani, Letizia ; Fafoutis, Xenofon. / Word Spotting in Background Music : a Behavioural Study. I: Cognitive Computation. 2019 ; Bind 11, Nr. 5. s. 711–718.
@article{0b175b132d99496bb1ae77b9c11ee54a,
title = "Word Spotting in Background Music: a Behavioural Study",
abstract = "Introduction Speech intelligibility in realistic environments is directly correlated with the ability of focusing attention on the sounds of interest while discarding the background noise and other competing stimuli. This work investigates task-driven auditory attention in noisy environments. Specifically, this study focuses on the ability to successfully execute a word spotting task while speech perception has to cope with the presence of music playing in the background. Methods The executed behavioural experiments consider different types of songs and explore how their distinct characteristics (such as dynamics or presence of distortion sound effects) affect the subjects’ task performance and, thus, the distribution of attention. Results Our results show that the ability of correctly separating the target sound from the background noise has a major impact on the performance of the subjects. Indeed, songs not presenting any distortion effect result in being more distracting than the ones with distortion, whose frequency spectrum envelop differentiates more from the one of the narrative. Furthermore, subjects performed the worst with songs characterised by high dynamics playing in the background, due to the unexpected changes capturing the attention of the listener.",
keywords = "Auditory attention, Auditory masking, Cocktail party, Music perception, Speech perception, Word spotting",
author = "Letizia Marchegiani and Xenofon Fafoutis",
year = "2019",
month = "10",
doi = "10.1007/s12559-019-09649-9",
language = "English",
volume = "11",
pages = "711–718",
journal = "Cognitive Computation",
issn = "1866-9964",
publisher = "Springer",
number = "5",

}

Word Spotting in Background Music : a Behavioural Study. / Marchegiani, Letizia; Fafoutis, Xenofon.

I: Cognitive Computation, Bind 11, Nr. 5, 10.2019, s. 711–718.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Word Spotting in Background Music

T2 - a Behavioural Study

AU - Marchegiani, Letizia

AU - Fafoutis, Xenofon

PY - 2019/10

Y1 - 2019/10

N2 - Introduction Speech intelligibility in realistic environments is directly correlated with the ability of focusing attention on the sounds of interest while discarding the background noise and other competing stimuli. This work investigates task-driven auditory attention in noisy environments. Specifically, this study focuses on the ability to successfully execute a word spotting task while speech perception has to cope with the presence of music playing in the background. Methods The executed behavioural experiments consider different types of songs and explore how their distinct characteristics (such as dynamics or presence of distortion sound effects) affect the subjects’ task performance and, thus, the distribution of attention. Results Our results show that the ability of correctly separating the target sound from the background noise has a major impact on the performance of the subjects. Indeed, songs not presenting any distortion effect result in being more distracting than the ones with distortion, whose frequency spectrum envelop differentiates more from the one of the narrative. Furthermore, subjects performed the worst with songs characterised by high dynamics playing in the background, due to the unexpected changes capturing the attention of the listener.

AB - Introduction Speech intelligibility in realistic environments is directly correlated with the ability of focusing attention on the sounds of interest while discarding the background noise and other competing stimuli. This work investigates task-driven auditory attention in noisy environments. Specifically, this study focuses on the ability to successfully execute a word spotting task while speech perception has to cope with the presence of music playing in the background. Methods The executed behavioural experiments consider different types of songs and explore how their distinct characteristics (such as dynamics or presence of distortion sound effects) affect the subjects’ task performance and, thus, the distribution of attention. Results Our results show that the ability of correctly separating the target sound from the background noise has a major impact on the performance of the subjects. Indeed, songs not presenting any distortion effect result in being more distracting than the ones with distortion, whose frequency spectrum envelop differentiates more from the one of the narrative. Furthermore, subjects performed the worst with songs characterised by high dynamics playing in the background, due to the unexpected changes capturing the attention of the listener.

KW - Auditory attention

KW - Auditory masking

KW - Cocktail party

KW - Music perception

KW - Speech perception

KW - Word spotting

UR - http://www.scopus.com/inward/record.url?scp=85067301836&partnerID=8YFLogxK

U2 - 10.1007/s12559-019-09649-9

DO - 10.1007/s12559-019-09649-9

M3 - Journal article

VL - 11

SP - 711

EP - 718

JO - Cognitive Computation

JF - Cognitive Computation

SN - 1866-9964

IS - 5

ER -