Kategorie: Sound Classification

New Tools & Data for Soundscape Synthesis and Online Audio Annotation

10/10/2017

We're glad to announce the release of two open-source tools and a new dataset developed as part of the SONYC project we hope will be of use to the community:

Scaper: a library for soundscape synthesis and augmentation

Automatically synthesize soundscapes with corresponding ground truth annotations
Useful for running controlled ML experiments (ASR, sound event detection, bioacoustic species recognition, etc.)
Useful for running controlled experiments to assess human annotation performance
Potentially useful for generating data for source separation experiments (might require some extra code)
Potentially useful for generating ambisonic soundscapes (definitely requires some extra code)

AudioAnnotator: a javascript web interface for annotating audio data

Developed in collaboration with Edith Law and her students at the University of Waterloo's HCI Lab
A web interface that allows users to annotate audio recordings
Supports 3 types of visualization (waveform, spectrogram, invisible)
Useful for crowdsourcing audio labels and running controlled experiments on crowdsourcing audio labels
Supports feedback mechanisms for providing real-time feedback to the user based on their annotations

URBAN-SED dataset: a new dataset for sound event detection

Includes 10,000 soundscapes with strongly labeled sound events generated using scaper
Totals almost 30 hours and includes close to 50,000 annotated sound events
Baseline convnet results on URBAN-SED are included in the scaper-paper.

Further information about scaper, the AudioAnnotator and the URBAN-SED dataset, including controlled experiments on the quality of crowdsourced human annotations as a function of visualization and soundscape complexity, are provided in the following papers:

Seeing sound: Investigating the effects of visualizations and complexity on crowdsourced audio annotations
M. Cartwright, A. Seals, J. Salamon, A. Williams, S. Mikloska, D. MacConnell, E. Law, J. Bello, and O. Nov.
Proceedings of the ACM on Human-Computer Interaction, 1(2), 2017.

Scaper: A Library for Soundscape Synthesis and Augmentation
J. Salamon, D. MacConnell, M. Cartwright, P. Li, and J. P. Bello.
In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA, Oct. 2017.

We hope you find these tools useful and look forward to receiving your feedback (and pull requests!).

Cheers, on behalf of the entire team,
Justin Salamon & Mark Cartwright.
â€‹--

0 Comments

Can the Internet of Things & AI Solve Urban Noise?

26/4/2017

0 Comments

New York City is a loud place. In fact, 9 of 10 adults in NYC are exposed to harmful levels of noise, which can lead to sleep loss, hearing loss and even heart disease. Can anything be done about it? The SONYC research project combines internet of things sensing technology, machine learning, data science and citizen science to tackle noise pollution head on at city scale. Come hear about a sensor that can recognize sounds like a human and how we plan to use it to improve quality of life in NYC.

The talk will be followed by my colleague and astrophysicist Federica Bianco with her talk:
Twinkle twinkle little city-light!

When: Wednesday, April 26, 2017, 7:30pm 10:00pm
Where: SingleCut Beersmiths, 19-33 37th Street NY, 11105 United States (map)
Registration: https://tasteofscience.org/ny-events/thescientificcity

0 Comments

Meet SONYC: Sounds of New York City

15/10/2015

0 Comments

Over the past two years I've been working together with a fantastic team of researchers on the SONYC: Sounds of New York City project. Check out our new video!

The objectives of SONYC are to create technological solutions for: (1) the systematic, constant monitoring of noise pollution at city scale; (2) the accurate description of acoustic environments in terms of its composing sources; (3) broadening citizen participation in noise reporting and mitigation; and (4) enabling city agencies to take effective, information-driven action for noise mitigation.

Noise pollution is one of the topmost quality of life issues for urban residents in the United States. It has been estimated that 9 out of 10 adults in New York City (NYC) are exposed to excessive noise levels, i.e. beyond the limit of what the EPA considers to be harmful. When applied to U.S. cities of more than 4 million inhabitants, such estimates extend to over 72 million urban residents.

To learn more about the SONYC project please check out the project website: wp.nyu.edu/sonyc

To read our publications on automatic urban sound classification as well as the development of low-cost, high-quality acoustic sensors, check out the project's publication page: wp.nyu.edu/sonyc/publications

0 Comments

Feature Learning with Deep Scattering for Urban Sound Analysis

10/6/2015

0 Comments

In this paper we evaluate the scattering transform as an alternative signal representation to the mel-spectrogram in the context of unsupervised feature learning for urban sound classification. We show that we can obtain comparable (or better) performance using the scattering transform whilst reducing both the amount of training data required for feature learning and the size of the learned codebook by an order of magnitude. In both cases the improvement is attributed to the local phase invariance of the representation. We also observe improved classification of sources in the background of the auditory scene, a result that provides further support for the importance of temporal modulation in sound segregation.

For further details please see our paper:

J. Salamon and J. P. Bello. "Feature Learning with Deep Scattering for Urban Sound Analysis", 2015 European Signal Processing Conference (EUSIPCO), Nice, France, August 2015.
[EURASIP][PDF][BibTex]

0 Comments

Announcing the Urban Sound dataset and taxonomy

23/10/2014

0 Comments

We are pleased to announce the release of UrbanSound, a dataset containing 27 hours of field-recordings with over 3000 labelled sound source occurrences from 10 sound classes. The dataset focuses on sounds that occur in urban acoustic environments.

To facilitate comparable research on urban sound source classification, we are also releasing a second version of this dataset, UrbanSound8K, with 8732 excerpts limited to 4 seconds (also with source labels), and pre-sorted into 10 stratified folds. In addition to the source ID both datasets also include a (subjective) salience label for each source occurrence: foreground / background.

The datasets are released for research purposes under a Creative Commons Attribution Noncommercial License, and are available online at the dataset companion website:

http://urbansounddataset.weebly.com/

This companion website also contains further information about each dataset, including the Urban Sound Taxonomy from which the 10 sound classes in this dataset were selected.

The datasets and taxonomy will be presented at the ACM Multimedia 2014 conference in Orlando in a couple of weeks. For those interested, please see our paper:

J. Salamon, C. Jacoby and J. P. Bello, "A Dataset and Taxonomy for Urban Sound Research", in Proc. 22nd ACM International Conference on Multimedia, Orlando USA, Nov. 2014.

For those attending ISMIR 2014 next week, I will also be there if you would like to discuss the datasets and taxonomy.

I hope you find the datasets useful for your work and look forward to seeing some of you at ISMIR and ACM-MM in the coming weeks!

0 Comments

New Tools & Data for Soundscape Synthesis and Online Audio Annotation

Can the Internet of Things & AI Solve Urban Noise?

Meet SONYC: Sounds of New York City

Feature Learning with Deep Scattering for Urban Sound Analysis

Announcing the Urban Sound dataset and taxonomy

NEWS

Archives

Categories