Automatic Soundscape Affect Recognition Using A Dimensional Approach

Fan, Jianyu; Thorogood, Miles; Pasquier, Philippe

doi:10.17743/jaes.2016.0044

Cited by 20 publications

(24 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For both arousal and valence, the loudness feature set performs well for all three datasets. This corresponds to the finds in previous studies [7,19]. Whereas rhythmic features perform better for arousal prediction of WCMED and valence prediction of CCMED, a paired t-test shows it is not significant.…”

Section: Feature Analysissupporting

confidence: 89%

“…Previous studies indicate arousal is easier to predict [7,14]. For both soundscape and music, arousal is determined by the level of eventfulness and activation.…”

Section: Discussionmentioning

confidence: 98%

“…A sound event detection (SED) system recognizes sound events in audio signals [6]. Soundscape emotion recognition (SER) is using computational methods for recognizing the perceived emotion of soundscape recordings [7]. We use a pretrained SED and SER models as feature extractors and use the extracted features as inputs to support vector regression (SVR) models.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Comparative Study of Western and Chinese Classical Music Based on Soundscape Models

Fan

Yang

Dong

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Whether literally or suggestively, the concept of soundscape is alluded in both modern and ancient music. In this study, we examine whether we can analyze and compare Western and Chinese classical music based on soundscape models. We addressed this question through a comparative study. Specifically, corpora of Western classical music excerpts (WCMED) and Chinese classical music excerpts (CCMED) were curated and annotated with emotional valence and arousal through a crowdsourcing experiment. We used a sound event detection (SED) and soundscape emotion recognition (SER) models with transfer learning to predict the perceived emotion of WCMED and CCMED. The results show that both SER and SED models could be used to analyze Chinese and Western classical music. The fact that SER and SED work better on Chinese classical music emotion recognition provides evidence that certain similarities exist between Chinese classical music and soundscape recordings, which permits transferability between machine learning models.

show abstract

Section: Feature Analysissupporting

confidence: 89%

“…Previous studies indicate arousal is easier to predict [7,14]. For both soundscape and music, arousal is determined by the level of eventfulness and activation.…”

Section: Discussionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study of Western and Chinese Classical Music Based on Soundscape Models

Fan

Yang

Dong

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, as in the first experiment, the focus was to observe the influence of the temporal structure in an environment, so sound markers or events have been removed. Such events, as semantic content, are suspected to significantly influence the overall rating of the sound environment [43]. These events and markers, present in the second experiment, might have masked the recency and trend effects that were observed in the first experiment.…”

mentioning

confidence: 91%

Global and Continuous Pleasantness Estimation of the Soundscape Perceived during Walking Trips through Urban Environments

et al. 2017

View full text Add to dashboard Cite

This paper investigates how the overall pleasantness of the sound environment of an urban walking trip can be estimated through acoustical measurements along the path. For this purpose, two laboratory experiments were carried out, during which controlled and natural 3-min audio and audiovisual sequences were presented. Participants were asked to continuously assess the pleasantness of the sound environment along the sequence, and globally at its end. The results reveal that the global sound pleasantness is principally explained by the average of the instantaneous sound pleasantness values. Accounting for recency or trend effects improved the estimates of the global sound pleasantness over controlled sound sequences, but their contribution is not significant for the second group of stimuli, which are based on natural audio sequences and include visual information. In addition, models for global and continuous pleasantness, as a function of the instantaneous sound pressure level L eq,1s , are proposed. The instantaneous sound pleasantness is found to be mainly impacted by the average sound level over the past 6 s. A logarithmic fading mechanism, extracted from psychological literature, is also proposed for this modelling, and slightly improves the estimations. Finally, the globally perceived sound pleasantness can be accurately estimated from the sound pressure level of the sound sequences, explaining about 60% of the variance in the global sound pleasantness ratings.

show abstract

“…Management of audio data typically involves assigning textual descriptors and allocating audio to a predefined category. Previous novel approaches to the problem of organising audio data into categories include: Augmenting the WordNet framework [1,2] with audio concepts in order to classify sounds [3,4]; using Gaver's [5] taxonomy based upon the mechanical properties of sound-causing events in an audio retrieval system [6]; classifying urban noise complaints [7]; classification by affect ratings [8]; and using hyponym generation from * This work was supported by EPSRC grant EP/N014111/1 'Making Sense of Sounds' and by European Commission H2020 research and innovation grant 688382 'AudioCommons'. web text with subsequent manual refinement [9].…”

Section: Introductionmentioning

confidence: 99%

Generalisation in Environmental Sound Classification: The ‘Making Sense of Sounds’ Data Set and Challenge

Kroos

Bones

Cao

et al. 2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Humans are able to identify a large number of environmental sounds and categorise them according to high-level semantic categories, e.g. urban sounds or music. They are also capable of generalising from past experience to new sounds when applying these categories. In this paper we report on the creation of a data set that is structured according to the top-level of a taxonomy derived from human judgements and the design of an associated machine learning challenge, in which strong generalisation abilities are required to be successful. We introduce a baseline classification system, a deep convolutional network, which showed strong performance with an average accuracy on the evaluation data of 80.8%. The result is discussed in the light of two alternative explanations: An unlikely accidental category bias in the sound recordings or a more plausible true acoustic grounding of the high-level categories.

show abstract

Automatic Soundscape Affect Recognition Using A Dimensional Approach

Cited by 20 publications

References 0 publications

A Comparative Study of Western and Chinese Classical Music Based on Soundscape Models

A Comparative Study of Western and Chinese Classical Music Based on Soundscape Models

Global and Continuous Pleasantness Estimation of the Soundscape Perceived during Walking Trips through Urban Environments

Generalisation in Environmental Sound Classification: The ‘Making Sense of Sounds’ Data Set and Challenge

Contact Info

Product

Resources

About