![enter image description here][2] This is a parallel competition to [**DCASE2019 challenge task 1C**](http://dcase.community/challenge2019/task-acoustic-scene-classification#subtask-c), intended to serve as public leaderboard for participants during the DCASE challenge. The competition is open for everybody and there is no requirement to submit to DCASE challenge. This subtask is concerned with acoustic scene classification where the test recording may be from a different environment than the 10 target classes, in which case it should be classified as "unknown", in a so-called open-set classification setup. The subtask uses TAU Urban Acoustic Scenes 2019 Openset dataset and some additional data providing examples of "unknown" acoustic scenes. The training material of this competition is the development dataset released for Task1C, and testing material consist of **similar material** to the official evaluation dataset in the DCASE challenge. The testing material amount in this competition is considerably lower than the official evaluation material in the DCASE challenge. There are three parallel competitions to DCASE challenge task 1 open in the Kaggle, one for each subtask: - **[Task1A Leaderboard, Acoustic Scene Classification](https://www.kaggle.com/c/dcase2019-task1a-leaderboard)**, single recording device used in the data collection, no external data allowed. - **[Task1B Leaderboard, Acoustic Scene Classification with mismatched recording devices](https://www.kaggle.com/c/dcase2019-task1b-leaderboard)**, multiple recording devices used in the data collection, no external data allowed. - **[Task1C Leaderboard, Open set Acoustic Scene Classification ](https://www.kaggle.com/c/dcase2019-task1c-leaderboard)**, classification on data that includes classes not encountered in the training data. *** ## **Note:** Official DCASE submission is **not done through Kaggle**. See [DCASE website](http://dcase.community/challenge2019/) for full information on how to submit to the challenge. *** ### Organizers - [Annamaria Mesaros](http://www.cs.tut.fi/~mesaros/), Assistant Professor, Tampere University, Finland - [Toni Heittola](http://www.cs.tut.fi/~heittolt/), Researcher, Tampere University, Finland - [Tuomas Virtanen](http://www.cs.tut.fi/~tuomasv/), Professor, Tampere University, Finland # Acoustic scene classification task The goal of acoustic scene classification is to classify a test recording into one of the provided predefined classes that characterizes the environment in which it was recorded — for example "park", "pedestrian street", "metro station". ![enter image description here][1] # Audio dataset The dataset for this task is the **TAU Urban Acoustic Scenes 2019 Openset** dataset, consisting of recordings from various acoustic scenes. This dataset extends the TUT Urban Acoustic Scenes 2018 Mobile dataset with other 6 cities to a total of 12 large European cities. For each scene class, recordings were done in different locations; for each recording location there are 5-6 minutes of audio. The original recordings were split into segments with a length of 10 seconds that are provided in individual files. Available information about the recordings include the following: acoustic scene class, city, and recording location. Acoustic scenes (10): - Airport - `airport` - Indoor shopping mall - `shopping_mall` - Metro station - `metro_station` - Pedestrian street - `street_pedestrian` - Public square - `public_square` - Street with medium level of traffic - `street_traffic` - Travelling by a tram - `tram` - Travelling by a bus - `bus` - Travelling by an underground metro - `metro` - Urban park - `park` Data was recorded in the following cities: - Amsterdam - Barcelona - Helsinki - Lisbon - London - Lyon - Madrid - Milan - Prague - Paris - Stockholm - Vienna The dataset was collected by Tampere University of Technology between 05/2018 - 11/2018. The data collection received funding from the European Research Council, grant agreement 637422 EVERYSOUND. ![enter image description here][4] **TAU Urban Acoustic Scenes 2019 OpenSet, Development dataset** is designed for researching open set classification problem in acoustic scene classification. In this problem, the test recording may be from a different environment than the 10 target classes. The dataset consists of 10-seconds audio segments from 10 acoustic scenes: - Airport - `airport` - Indoor shopping mall - `shopping_mall` - Metro station - `metro_station` - Pedestrian street - `street_pedestrian` - Public square - `public_square` - Street with medium level of traffic - `street_traffic` - Travelling by a tram - `tram` - Travelling by a bus - `bus` - Travelling by an underground metro - `metro` - Urban park - `park` In addition, material for Unknown scene `unknown` is provided from 4 scenes: - Beach - `beach`, extracted from TUT Acoustic scenes 2017 dataset - Library - `library`, extracted from TUT Acoustic scenes 2017 dataset - Office - `office`, extracted from TUT Acoustic scenes 2017 dataset - Public event - `public_event` *** ### [TAU Urban Acoustic Scenes 2019 OpenSet, Development dataset (17.8 GB) ](https://doi.org/10.5281/zenodo.2591503) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.2591503.svg)](https://doi.org/10.5281/zenodo.2591503) *** **TAU Urban Acoustic Scenes 2019 OpenSet, Leaderboard dataset** is used in this competition as test dataset. This dataset is used only in this competition, not in the actual DCASE2019 Challenge. *** ### [TAU Urban Acoustic Scenes 2019 OpenSet, Leaderboard dataset (1.3 GB) ](https://zenodo.org/record/2673006) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.2673006.svg)](https://doi.org/10.5281/zenodo.2673006) *** ## Recording procedure Recordings were made using four devices that captured audio simultaneously. The main recording device consists in [Soundman OKM II Klassik/studio A3](http://www.soundman.de/en/products/), electret binaural microphone and a [Zoom F8](https://www.zoom.co.jp/products/handy-recorder/zoom-f8-multitrack-field-recorder) audio recorder using 48kHz sampling rate and 24 bit resolution. The microphones are specifically made to look like headphones, being worn in the ears. As an effect of this, the recorded audio is very similar to the sound that reaches the human auditory system of the person wearing the equipment. This equipment is further referred to as device A. The other devices are commonly available customer devices: device B is a Samsung Galaxy S7, device C is IPhone SE, and device D is a GoPro Hero5 Session. All simultaneous recordings are time synchronized. ## Baseline system The baseline system provides a simple entry-level approach that gives reasonable results in the subtasks of Task 1. The baseline system is built on [dcase_util toolbox](https://github.com/DCASE-REPO/dcase_util). *** ### [DCASE2019 Task 1 Baseline code repository](https://github.com/toni-heittola/dcase2019_task1_baseline) *** ### System description The baseline system implements a convolutional neural network (CNN) based approach, where log mel-band energies are first extracted for each 10-second signal, and a network consisting of two CNN layers and one fully connected layer is trained to assign scene labels to the audio signals. More detailed description and system accuracy on development dataset can be found from readme file in the [code repository](https://github.com/toni-heittola/dcase2019_task1_baseline/blob/master/README.md). [1]: http://dcase.community/images/tasks/challenge2019/task1_acoustic_scene_classification_openset.png [2]: http://dcase.community/images/logos/dcase/dcase2019_challenge.png [3]: http://d33wubrfki0l68.cloudfront.net/15556a316bea611e8f73980845a7ef41dd162de9/05afc/images/tasks/challenge2019/task1_acoustic_scene_classification.png [4]: http://d33wubrfki0l68.cloudfront.net/750a7452e2c66bfb113a1b011ecc888f03245c99/0e821/images/sponsors/erc.jpg