Word Spotting in Background Music: a Behavioural Study

Marchegiani, Letizia; Fafoutis, Xenofon

doi:10.1007/s12559-019-09649-9

Cited by 4 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies present small samples of adult participants, making it difficult to generalize the results to the general adult population (≤24 adult participants; Amezcua et al, 2005 ; Speer, 2011 ; Giannouli, 2012 ; Fernandez et al, 2019 ; Cloutier et al, 2020 ). In addition, most of the time, non-auditory (e.g., silence) and auditory (e.g., noises with sound characteristics similar to those of music) control conditions were lacking ( Darrow et al, 2006 ; Marchegiani and Fafoutis, 2019 ; Deng and Wu, 2020 ; Cloutier et al, 2020 ). There were also methodological limitations regarding the choice of the sound material used.…”

Section: Introductionmentioning

confidence: 99%

“…There were also methodological limitations regarding the choice of the sound material used. For example, some studies have presented music with words (e.g., Darrow et al, 2006 ; Speer, 2011 ; Marchegiani and Fafoutis, 2019 ; Deng and Wu, 2020 ), which has generally resulted in a deleterious effect on performance. However, several studies have previously shown that the presence of speech or words in a sound environment tends to negatively affect cognitive performance in comparison with a speechless sound environment (e.g., Salamé and Baddeley, 1989 ; Szalma and Hancock, 2011 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Emotional Effect of Background Music on Selective Attention of Adults

et al. 2021

View full text Add to dashboard Cite

Daily activities can often be performed while listening to music, which could influence the ability to select relevant stimuli while ignoring distractors. Previous studies have established that the level of arousal of music (e.g., relaxing/stimulating) has the ability to modulate mood and affect the performance of cognitive tasks. The aim of this research was to explore the effect of relaxing and stimulating background music on selective attention. To this aim, 46 healthy adults performed a Stroop-type task in five different sound environments: relaxing music, stimulating music, relaxing music-matched noise, stimulating music-matched noise, and silence. Results showed that response times for incongruent and congruent trials as well as the Stroop interference effect were similar across conditions. Interestingly, results revealed a decreased error rate for congruent trials in the relaxing music condition as compared to the relaxing music-matched noise condition, and a similar tendency between relaxing music and stimulating music-matched noise. Taken together, the absence of difference between background music and silence conditions suggest that they have similar effects on adult’s selective attention capacities, while noise seems to have a detrimental impact, particularly when the task is easier cognitively. In conclusion, the type of sound stimulation in the environment seems to be a factor that can affect cognitive tasks performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Emotional Effect of Background Music on Selective Attention of Adults

et al. 2021

View full text Add to dashboard Cite

show abstract

Exploration on Automatic Recommendation System for Video Background Music Based on Machine Learning

Liu

2024

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

CochleaNet: A robust language-independent audio-visual model for real-time speech enhancement

et al. 2020

View full text Add to dashboard Cite

Noisy situations cause huge problems for suffers of hearing loss as hearing aids often make the signal more audible but do not always restore the intelligibility.In noisy settings, humans routinely exploit the audio-visual (AV) nature of the speech to selectively suppress the background noise and to focus on the target speaker. In this paper, we present a causal, language, noise and speaker independent AV deep neural network (DNN) architecture for speech enhancement (SE).The model exploits the noisy acoustic cues and noise robust visual cues to focus on the desired speaker and improve the speech intelligibility. To evaluate the proposed SE framework a first of its kind AV binaural speech corpus, called AS-PIRE, is recorded in real noisy environments including cafeteria and restaurant.We demonstrate superior performance of our approach in terms of objective measures and subjective listening tests over the state-of-the-art SE approaches as well as recent DNN based SE models. In addition, our work challenges a popular belief that a scarcity of multi-language large vocabulary AV corpus and wide variety of noises is a major bottleneck to build a robust language, speaker and noise independent SE systems. We show that a model trained on synthetic mixture of Grid corpus (with 33 speakers and a small English vocabulary) and ChiME 3 Noises (consisting of only bus, pedestrian, cafeteria, and street noises) generalise well not only on large vocabulary corpora but also on completely unrelated languages (such as Mandarin), wide variety of speakers and noises.

show abstract

Word Spotting in Background Music: a Behavioural Study

Cited by 4 publications

References 32 publications

The Emotional Effect of Background Music on Selective Attention of Adults

The Emotional Effect of Background Music on Selective Attention of Adults

Exploration on Automatic Recommendation System for Video Background Music Based on Machine Learning

CochleaNet: A robust language-independent audio-visual model for real-time speech enhancement

Contact Info

Product

Resources

About