|
View: |
Part 1: Document Description
|
|
Citation |
|
|---|---|
|
Title: |
ARAUS: A Large-Scale Dataset and Baseline Models of Affective Responses to Augmented Urban Soundscapes |
|
Identification Number: |
doi:10.21979/N9/9OTEVX |
|
Distributor: |
DR-NTU (Data) |
|
Date of Distribution: |
2022-07-05 |
|
Version: |
4 |
|
Bibliographic Citation: |
Ooi, Kenneth; Ong, Zhen-Ting; Watcharasupat, Karn N.; Lam, Bhan; Hong, Joo Young; Gan, Woon-Seng, 2022, "ARAUS: A Large-Scale Dataset and Baseline Models of Affective Responses to Augmented Urban Soundscapes", https://doi.org/10.21979/N9/9OTEVX, DR-NTU (Data), V4 |
|
Citation |
|
|
Title: |
ARAUS: A Large-Scale Dataset and Baseline Models of Affective Responses to Augmented Urban Soundscapes |
|
Alternative Title: |
ARAUS |
|
Identification Number: |
doi:10.21979/N9/9OTEVX |
|
Authoring Entity: |
Ooi, Kenneth (Nanyang Technological University) |
|
Ong, Zhen-Ting (Nanyang Technological University) |
|
|
Watcharasupat, Karn N. (Nanyang Technological University) |
|
|
Lam, Bhan (Nanyang Technological University) |
|
|
Hong, Joo Young (Nanyang Technological University) |
|
|
Gan, Woon-Seng (Nanyang Technological University) |
|
|
Software used in Production: |
Python |
|
Grant Number: |
Prime Minister’s Office COT-V4-2020-1 |
|
Distributor: |
DR-NTU (Data) |
|
Access Authority: |
Ooi, Kenneth |
|
Depositor: |
Ooi, Wen Rui Kenneth |
|
Date of Deposit: |
2022-03-30 |
|
Holdings Information: |
https://doi.org/10.21979/N9/9OTEVX |
|
Study Scope |
|
|
Keywords: |
Computer and Information Science, Engineering, Computer and Information Science, Engineering, soundscape, soundscape augmentation, dataset, deep neural network, regression, auditory masking |
|
Abstract: |
This repository contains the <b>ARAUS</b> dataset, a publicly-available dataset (comprising a 5-fold training/validation set and an independent test set) of 25,440 unique subjective perceptual responses to augmented soundscapes presented as audio-visual stimuli. Each augmented soundscape is made by digitally adding "maskers" (bird, water, wind, traffic, construction, or silence) to urban soundscape recordings at fixed soundscape-to-masker ratios. This mimics a real-life soundscape augmentation system, whereby a speaker (or some other sound source) is used to add "maskers" to an actual urban soundscape. <br><br> Responses were then collected by asking participants to rate how pleasant, annoying, eventful, uneventful, vibrant, monotonous, chaotic, calm, and appropriate each augmented soundscape was. <br><br> The data in this repository aims to form a benchmark for fair comparisons of models for the prediction and analysis of perceptual attributes of soundscapes. Please refer to our publication submitted to <i>IEEE Transactions on Affective Computing</i> for more details regarding the data collection, annotation, and processing methodologies for the creation of the dataset: <br><br> Kenneth Ooi, Zhen-Ting Ong, Karn N. Watcharasupat, Bhan Lam, Joo Young Hong, Woon-Seng Gan, ARAUS: A large-scale dataset and baseline models of affective responses to augmented urban soundscapes, <i>IEEE Transactions on Affective Computing</i>, doi: 10.1109/TAFFC.2023.3247914. <br><br> Replication code and baseline models that we have trained using the <b>ARAUS</b> dataset can be found at our GitHub repository: <a href="https://github.com/ntudsp/araus-dataset-baseline-models">https://github.com/ntudsp/araus-dataset-baseline-models</a> |
|
Kind of Data: |
Survey data |
|
Kind of Data: |
Audio data |
|
Methodology and Processing |
|
|
Sources Statement |
|
|
Data Access |
|
|
Notes: |
This file is an archival copy of the raw binaural recordings of soundscapes in the Urban Soundscapes of the World (USotW) database (https://urban-soundscapes.s3.eu-central-1.wasabisys.com/soundscapes/index.html). Since the recordings are still publicly available at the USotW database website, and we do not have a license to distribute those recordings on our end, you may download the USotW recordings directly from their website instead. |
|
Other Study Description Materials |
|
|
Related Studies |
|
|
Replication code and baseline models that we have trained using the ARAUS dataset can be found at our GitHub repository: <a href="https://github.com/ntudsp/araus-dataset-baseline-models">https://github.com/ntudsp/araus-dataset-baseline-models</a> |
|
|
Related Publications |
|
|
Citation |
|
|
Identification Number: |
2207.01078 |
|
Bibliographic Citation: |
Ooi, K., Ong, Z. T., Watcharasupat, K. N., Lam, B., Hong, J. Y., & Gan, W. S. (2022). ARAUS: A Large-Scale Dataset and Baseline Models of Affective Responses to Augmented Urban Soundscapes, arXiv preprint. |
|
Citation |
|
|
Identification Number: |
10.1109/TAFFC.2023.3247914 |
|
Bibliographic Citation: |
Ooi, K., Ong, Z. T., Watcharasupat, K. N., Lam, B., Hong, J. Y., & Gan, W. S. (2022). ARAUS: A Large-Scale Dataset and Baseline Models of Affective Responses to Augmented Urban Soundscapes, IEEE Transactions on Affective Computing. |
|
Citation |
|
|
Identification Number: |
10356/179452 |
|
Bibliographic Citation: |
Ooi, K. W. R. (2024). Artificial intelligence for urban soundscape augmentation: a benchmark dataset, probabilistic models, and real-life validation. Doctoral thesis, Nanyang Technological University, Singapore. |
|
Label: |
datav2.zip |
|
Notes: |
application/zip |
|
Label: |
data.zip |
|
Notes: |
application/zip |
|
Label: |
figures.zip |
|
Notes: |
application/zip |
|
Label: |
maskersv2.zip |
|
Notes: |
application/zip |
|
Label: |
maskers.zip |
|
Text: |
This file contains the masker recordings (resampled to 44.1 kHz) for the 5-fold cross-validation set and independent test set. |
|
Notes: |
application/zip |
|
Label: |
soundscapes_raw.zip |
|
Text: |
This file is an archival copy of the raw binaural recordings of soundscapes in the Urban Soundscapes of the World (USotW) database. Please contact the USotW team at https://urban-soundscapes.org/contact/ if you wish to obtain a copy of the recordings. |
|
Notes: |
application/zip |
|
Label: |
soundscapes.zip |
|
Text: |
This file contains the raw binaural recordings of soundscapes (resampled to 44.1 kHz) in the test set. These recordings were made by us. |
|
Notes: |
application/zip |
|
Label: |
videos.zip |
|
Text: |
This file contains the raw 360-degree videos of the soundscapes in the test set. These recordings were made by us. |
|
Notes: |
application/zip |