You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.
\n\nThere is no maximum team size.
\n\nYou may submit a maximum of 1 entries per day.
\nYou may select up to 4 final submissions for judging.
\n\nStart Date: TBA
\nMerger Deadline: None
\nEntry Deadline: None
\nEnd Date: 2/1/2014 12:00 AM UTC
\n\t\n\nUse of external data is not allowed. Data from another task or subtask of DCASE2018 is considered also external data.
\n\nManipulation of provided training and development data is allowed . The development dataset (training dataset) can be augmented without use of external data (e.g. by mixing data sampled from a pdf or using techniques such as pitch shifting or time stretching).\n\n
\nParticipants are not allowed to make subjective judgments of the test data, nor to annotate it. The test data cannot be used to train the submitted system; the use of statistics about the test data in the decision making is also forbidden. Classification decision must be done independently for each test sample. One cannot use information from other test items when predicting the scene label.\n
\n\nfilename\tscene_label\tidentifier\tsource_label\naudio/airport-barcelona-0-0-a.wav\tairport\tbarcelona-0\ta\naudio/airport-barcelona-0-1-a.wav\tairport\tbarcelona-0\ta\n....\naudio/bus-barcelona-17-706-a.wav\tbus\tbarcelona-17\ta\naudio/bus-helsinki-18-707-a.wav\tbus\thelsinki-18\ta\naudio/bus-helsinki-18-708-a.wav\tbus\thelsinki-18\ta\n...\naudio/metro-london-46-1402-b.wav\tmetro\tlondon-46\tb\naudio/metro-stockholm-57-1699-b.wav\tmetro\tstockholm-57\tb\n...\naudio/street_traffic-vienna-178-5490-c.wav\tstreet_traffic\tvienna-178\tc\naudio/tram-helsinki-182-5639-c.wav\ttram\thelsinki-182\tc\n...\naudio/tram-vienna-285-8637-a.wav\ttram\tvienna-285\ta\naudio/tram-vienna-285-8638-a.wav\ttram\tvienna-285\ta\naudio/tram-vienna-285-8639-a.wav\ttram\tvienna-285\ta\n\n\nNaming convention for audio segments is
file naming convention: [scene label]-[city]-[location id]-[segment id]-[device id].wav\n\n`source_label` field in the meta data or `[device id]` field in the audio segment filename is used to denote the used recording device. \n\nThe dataset is provided with single fold cross-validation set (training / testing) to ease the usage of the development dataset. Participants can do their own cross-validation setup too. File lists assigning segments to the subsets are provided under directory `evaluation_setup`. \n\n## Testing dataset\n\nSimilarly to the development dataset, there are three methods for obtaining the dataset.\n\n1) Downloading it directly:\n\n***\n\n### [TUT Urban Acoustic Scenes 2018 Mobile, Leaderboard dataset (2.3 GB) ](https://zenodo.org/record/1245184)\n\n[](https://doi.org/10.5281/zenodo.1245184)\n\n***\n\n2) Dataset can be downloaded using the provided download script:\n\n`python task1b_dataset_downloader.py -d test`\n\n3) If you are using official [DCASE2018 Challenge baseline system](https://github.com/DCASE-REPO/dcase2018_baseline/tree/master/task1) you can use it to download the dataset too:\n\n`python task1b.py -m leaderboard --download_dataset datasets/`\n\n## Dataset license\n\n
\n Copyright (c) 2018 Tampere University of Technology and its licensors \n All rights reserved.\n Permission is hereby granted, without written agreement and without license or royalty \n fees, to use and copy the TUT Urban Acoustic Scenes 2018 Mobile (“Work”) described in this document \n and composed of audio and metadata. This grant is only for experimental and non-commercial \n purposes, provided that the copyright notice in its entirety appear in all copies of this Work, \n and the original source of this Work, (Audio Research Group from Laboratory of Signal\n Processing at Tampere University of Technology), \n is acknowledged in any publication that reports research using this Work.\n Any commercial use of the Work or any part thereof is strictly prohibited. \n Commercial use include, but is not limited to:\n - selling or reproducing the Work\n - selling or distributing the results or content achieved by use of the Work\n - providing services by using the Work. \n \n IN NO EVENT SHALL TAMPERE UNIVERSITY OF TECHNOLOGY OR ITS LICENSORS BE LIABLE TO ANY PARTY\n FOR DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE\n OF THIS WORK AND ITS DOCUMENTATION, EVEN IF TAMPERE UNIVERSITY OF TECHNOLOGY OR ITS\n LICENSORS HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.\n \n TAMPERE UNIVERSITY OF TECHNOLOGY AND ALL ITS LICENSORS SPECIFICALLY DISCLAIMS ANY\n WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND \n FITNESS FOR A PARTICULAR PURPOSE. THE WORK PROVIDED HEREUNDER IS ON AN \"AS IS\" BASIS, AND \n THE TAMPERE UNIVERSITY OF TECHNOLOGY HAS NO OBLIGATION TO PROVIDE MAINTENANCE, SUPPORT, \n UPDATES, ENHANCEMENTS, OR MODIFICATIONS.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "![enter image description here][1]\n\nThis is a parallel competition to DCASE2018 challenge task 1B, 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. \n\nThe training material of this competition is the development dataset released for Task1B, 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. \n\nThere are three parallel competitions to DCASE challenge task 1 open in the Kaggle, one for each subtask:\n\n- **[Task1A Leaderboard, Acoustic Scene Classification](https://www.kaggle.com/c/dcase2018-task1a-leaderboard)**, single recording device used in the data collection, no external data allowed. \n\n- **[Task1B Leaderboard, Acoustic Scene Classification with mismatched recording devices](https://www.kaggle.com/c/dcase2018-task1b-leaderboard)**, multiple recording devices used in the data collection, no external data allowed.\n\n- **[Task1C Leaderboard, Acoustic Scene Classification with use of external data](https://www.kaggle.com/c/dcase2018-task1c-leaderboard)**, the same task setup as in task 1A, but external data is allowed in a limited way.\n\n***\n## **Note:** Official DCASE submission is **not done through Kaggle**. See [DCASE website](http://dcase.community/challenge2018/submission) for full information on how to submit to the challenge.\n***\n\n### Organizers\n\n- [Annamaria Mesaros](http://www.cs.tut.fi/~mesaros/), Postdoctoral researcher, Tampere University of Technology, Finland\n- [Toni Heittola](http://www.cs.tut.fi/~heittolt/), Researcher, Tampere University of Technology, Finland\n- [Tuomas Virtanen](http://www.cs.tut.fi/~tuomasv/), Professor, Tampere University of Technology, Finland\n\n# Acoustic scene classification task\n\nThe 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\". \n\n![Overview of acoustic scene classification system.][2]\n\n# Audio dataset\n\nThe dataset for this task is the **TUT Urban Acoustic Scenes 2018** dataset, consisting of recordings from various acoustic scenes. The dataset was recorded in six large European cities, in different locations for each scene class. 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. \n\nAcoustic scenes for the task (10):\n\n- Airport - `airport`\n- Indoor shopping mall - `shopping_mall`\n- Metro station - `metro_station`\n- Pedestrian street - `street_pedestrian`\n- Public square - `public_square`\n- Street with medium level of traffic - `street_traffic`\n- Travelling by a tram - `tram`\n- Travelling by a bus - `bus`\n- Travelling by an underground metro - `metro`\n- Urban park - `park`\n\nThe dataset was collected by Tampere University of Technology between 01/2018 - 03/2018. The data collection received funding from the European Research Council, grant agreement 637422 EVERYSOUND.\n\n[![ERC][3]](https://erc.europa.eu/)\n\n**TUT Urban Acoustic Scenes 2018 Mobile, Development dataset** contains material recorded with three devices (A, B and C). Each acoustic scene has 864 segments (144 minutes of audio) recorded with device A (main device) and 72 segments of parallel audio (12 minutes) each recorded with devices B and C. The dataset contains in total 28 hours of audio.\n\n***\n\n### [TUT Urban Acoustic Scenes 2018 Mobile, Development dataset (11.3 GB) ](https://zenodo.org/record/1228235)\n\n[](https://doi.org/10.5281/zenodo.1228235)\n\n***\n\n**TUT Urban Acoustic Scenes 2018 Mobile, Leaderboard dataset** contains only material recorded with devices B and C, and it is used in this competition as test dataset. This dataset is used only in this competition, not in the actual DCASE2018 Challenge.\n\n***\n\n### [TUT Urban Acoustic Scenes 2018 Mobile, Leaderboard dataset (2.3 GB) ](https://zenodo.org/record/1245184)\n\n[](https://doi.org/10.5281/zenodo.1245184)\n\n***\n\n## Recording procedure\n\nRecordings were made using four devices that captured audio simultaneously. \n\nThe 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.\n\nThree other commonly available customer devices (e.g. smartphones, cameras) were used, handled in typical ways by the person doing recordings (e.g. hand held). We further refer to these devices as B, C, and D. The audio recordings from these devices are of different quality than device A. All simultaneous recordings are time synchronized. \n\n## Baseline system\n\nThe baseline system provides a simple entry-level state-of-the-art 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).\n\n***\n\n### [DCASE2018 Task 1 Baseline code repository](https://github.com/DCASE-REPO/dcase2018_baseline/tree/master/task1)\n\n***\n\nParticipants are strongly encouraged to build their own systems by extending the provided baseline system. The system has all needed functionality for the dataset handling, acoustic feature storing and accessing, acoustic model training and storing, and evaluation. The modular structure of the system enables participants to modify the system to their needs. The baseline system is a good starting point especially for the entry level researchers to familiarize themselves with the acoustic scene classification problem.\n\nIf participants plan to publish their code to the DCASE community after the challenge, building their approach on the baseline system will make their code more accessible to the community. DCASE organizers strongly encourage participants to share their code in any form after the challenge.\n\n### System description\n\nThe 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. \n\nMore detailed description and system accuracy on development dataset can be found from readme file in the [code repository](https://github.com/DCASE-REPO/dcase2018_baseline/blob/master/README.md).\n\n [1]: http://d33wubrfki0l68.cloudfront.net/341ee23023e02c446dd7eb9ec3657944829e7dad/5b709/images/logos/dcase/dcase2018_challenge.png\n [2]: http://d33wubrfki0l68.cloudfront.net/15556a316bea611e8f73980845a7ef41dd162de9/7572a/images/tasks/challenge2018/task1_acoustic_scene_classification.png\n [3]: http://d33wubrfki0l68.cloudfront.net/750a7452e2c66bfb113a1b011ecc888f03245c99/0e821/images/sponsors/erc.jpg", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The participants will be ranked based on the accuracy of their predictions. The evaluation metric for this competition is the prediction accuracy, the proportion of 10-second test recordings for which your algorithm makes the correct prediction.\n\n## Submission Format\n\nSubmission files should be in csv format and contain two columns: Id and Prediction. The first column of the csv file is the test sample ID (0,1,2,3,...,1199) and the second column is the class name predicted for that sample by your algorithm.\n\nThe file should contain a header and have the following format:\n\n
Id,Scene_label\n\n**Note:** The submission format is slightly different to the one used in DCASE challenge due to requirements of the Kaggle system.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }
0,metro_station
1,bus
2,metro
...
1199,park