SONYC Urban Sound Tagging (SONYC-UST): A Multilabel Dataset from an Urban
                        Acoustic Sensor Network

Cartwright, Mark; Méndez, Ana Elisa Méndez; Cramer, Jason; Lostanlen, Vincent; Dove, Graham; Wu, Ho-Hsiang; Nov, Oded; Bello, Juan Pablo

doi:10.33682/j5zw-2t88

Cited by 46 publications

(44 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the embeddings zi and zj are obtained with a single instantiation of the encoder and projection head (see shared weights in Figure 1). [23,24,25,21,26]). The limited dataset scope implies, however, that the learned representations are not transferable to unrelated datasets or downstream tasks, forcing to conduct an in-domain evaluation.…”

Section: Methodsmentioning

confidence: 99%

Unsupervised Contrastive Learning of Sound Event Representations

Fonseca

Ortego

McGuinness

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data-a common scenario in sound event research. In this work, we explore unsupervised contrastive learning as a way to learn sound event representations. To this end, we propose to use the pretext task of contrasting differently augmented views of sound events. The views are computed primarily via mixing of training examples with unrelated backgrounds, followed by other data augmentations. We analyze the main components of our method via ablation experiments. We evaluate the learned representations using linear evaluation, and in two in-domain downstream sound event classification tasks, namely, using limited manually labeled data, and using noisy labeled data. Our results suggest that unsupervised contrastive pre-training can mitigate the impact of data scarcity and increase robustness against noisy labels.

show abstract

Section: Methodsmentioning

confidence: 99%

Unsupervised Contrastive Learning of Sound Event Representations

Fonseca

Ortego

McGuinness

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…For training the downstream classifier from the student embeddings, we leverage SONYC Urban Sound Tagging (SONYC-UST) [22], a fraction of SONYC data annotated through crowdsourcing initiatives on the Zooniverse [23] platform, as the Downstream dataset. It is a multi-label dataset consisting of 3068 annotated 10second audio recordings belonging to 8 classes: engine, machineryimpact, non-machinery-impact, powered-saw, alert-signal, music, human-voice, and dog.…”

Section: ℝ Nmentioning

confidence: 99%

Specialized Embedding Approximation for Edge Intelligence: A Case Study in Urban Sound Classification

Srivastava

Roy

Cartwright

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Embedding models that encode semantic information into lowdimensional vector representations are useful in various machine learning tasks with limited training data. However, these models are typically too large to support inference in small edge devices, which motivates training of smaller yet comparably predictive student embedding models through knowledge distillation (KD). While knowledge distillation traditionally uses the teacher's original training dataset to train the student, we hypothesize that using a dataset similar to the student's target domain allows for better compression and training efficiency for the said domain, at the cost of reduced generality across other (non-pertinent) domains. Hence, we introduce Specialized Embedding Approximation (SEA) to train a student featurizer to approximate the teacher's embedding manifold for a given target domain. We demonstrate the feasibility of SEA in the context of acoustic event classification for urban noise monitoring and show that leveraging a dataset related to this target domain not only improves the baseline performance of the original embedding model but also yields competitive students with >1 order of magnitude lesser storage and activation memory. We further investigate the impact of using random and informed sampling techniques for dimensionality reduction in SEA.

show abstract

“…Another WASN-based project that has collected real operation acoustic samples is the SONYC (Sounds of New York) project [32]. Bello provides a simplified taxonomy of the sounds of the city by means of a two-level hierarchy, dividing them into eight coarse categories and 23 fine labels [33]. The generated dataset is composed of 2351 recordings in the train split and 443 in the validation split, making a total of 2794 audio samples of 10 s each.…”

Section: Related Workmentioning

confidence: 99%

BCNDataset: Description and Analysis of an Annotated Night Urban Leisure Sound Dataset

et al. 2020

View full text Add to dashboard Cite

Acoustic pollution has been associated with adverse effects on the health and life expectancy of people, especially when noise exposure happens during the nighttime. With over half of the world population living in urban areas, acoustic pollution is an important concern for city administrators, especially those focused on transportation and leisure noise. Advances in sensor and network technologies made the deployment of Wireless Acoustic Sensor Networks (WASN) possible in cities, which, combined with artificial intelligence (AI), can enable smart services for their citizens. However, the creation of such services often requires structured environmental audio databases to train AI algorithms. This paper reports on an environmental audio dataset of 363 min and 53 s created in a lively area of the Barcelona city center, which targeted traffic and leisure events. This dataset, which is free and publicly available, can provide researchers with real-world acoustic data to help the development and testing of sound monitoring solutions for urban environments.

show abstract

SONYC Urban Sound Tagging (SONYC-UST): A Multilabel Dataset from an Urban Acoustic Sensor Network

Cited by 46 publications

References 0 publications

Unsupervised Contrastive Learning of Sound Event Representations

Unsupervised Contrastive Learning of Sound Event Representations

Specialized Embedding Approximation for Edge Intelligence: A Case Study in Urban Sound Classification

BCNDataset: Description and Analysis of an Annotated Night Urban Leisure Sound Dataset

Contact Info

Product

Resources

About