dcase_models.data.TAUUrbanAcousticScenes2019¶

class dcase_models.data.TAUUrbanAcousticScenes2019(dataset_path)[source]¶

Bases: dcase_models.data.datasets._TAUUrbanAcousticScenes

TAU Urban Acoustic Scenes 2019 dataset.

This class inherits all functionality from Dataset and defines specific attributes and methods for TAU Urban Acoustic Scenes 2019.

Url: https://zenodo.org/record/2589280

A. Mesaros, T. Heittola, and T. Virtanen. “A multi-devicedataset for urban acoustic scene classification”. Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE 2018). November 2018.

Parameters:	dataset_path : str Path to the dataset folder. This is the path to the folder where the complete dataset will be downloaded, decompressed and handled. It is expected to use a folder name that represents the dataset unambiguously (e.g. ../datasets/TAUUrbanAcousticScenes2019).

Examples

To work with TAUUrbanAcousticScenes2019 dataset, just initialize this class with the path to the dataset.

>>> from dcase_models.data.datasets import TAUUrbanAcousticScenes2019
>>> dataset = TAUUrbanAcousticScenes2019(
    '../datasets/TAUUrbanAcousticScenes2019')

Then, you can download the dataset and change the sampling rate.

>>> dataset.download()
>>> dataset.change_sampling_rate(22050)

__init__(dataset_path)[source]¶: Init Dataset

Methods

`__init__`(dataset_path)	Init Dataset
`build`()	Builds the dataset.
`change_sampling_rate`(new_sr)	Changes the sampling rate of each wav file in audio_path.
`check_if_downloaded`()	Checks if the dataset was downloaded.
`check_sampling_rate`(sr)	Checks if dataset was resampled before.
`convert_to_wav`([remove_original])	Converts each file in the dataset to wav format.
`download`([force_download])	Downloads and decompresses the dataset from zenodo.
`generate_file_lists`()	Creates file_lists, a dict that includes a list of files per fold.
`get_annotations`(file_name, features, …)	Returns the annotations of the file in file_path.
`get_audio_paths`([sr])	Returns paths to the audio folder.
`set_as_downloaded`()	Saves a download.txt file in dataset_path as a downloaded flag.

build()¶

Builds the dataset.

Define specific attributes of the dataset. It’s mandatory to define audio_path, fold_list and label_list. Other attributes may be defined here (url, authors, etc.).

change_sampling_rate(new_sr)¶

Changes the sampling rate of each wav file in audio_path.

Creates a new folder named audio_path{new_sr} (i.e audio22050) and converts each wav file in audio_path and save the result in the new folder.

Parameters:	sr : int Sampling rate.

check_if_downloaded()¶

Checks if the dataset was downloaded.

Just checks if exists download.txt file.

Further checks in the future.

check_sampling_rate(sr)¶

Checks if dataset was resampled before.

For now, only checks if the folder {audio_path}{sr} exists and each wav file present in audio_path is also present in {audio_path}{sr}.

Parameters:	sr : int Sampling rate.
Returns:	bool True if the dataset was resampled before.

convert_to_wav(remove_original=False)¶

Converts each file in the dataset to wav format.

If remove_original is False, the original files will be deleted

Parameters:	remove_original : bool Remove original files.

download(force_download=False)[source]¶

Downloads and decompresses the dataset from zenodo.

Parameters:	zenodo_url : str URL with the zenodo files. e.g. ‘https://zenodo.org/record/12345/files’ zenodo_files : list of str List of files. e.g. [‘file1.tar.gz’, ‘file2.tar.gz’, ‘file3.tar.gz’] force_download : bool If True, download the dataset even if was downloaded before.
Returns:	bool True if the downloading process was successful.

generate_file_lists()¶

Creates file_lists, a dict that includes a list of files per fold.

Each dataset has a different way of organizing the files. This function defines the dataset structure.

get_annotations(file_name, features, time_resolution)¶

Returns the annotations of the file in file_path.

Parameters:	file_path : str Path to the file features : ndarray nD array with the features of file_path time_resolution : float Time resolution of the features
Returns:	ndarray Annotations of the file file_path Expected output shape: (features.shape[0], len(self.label_list))

get_audio_paths(sr=None)¶

Returns paths to the audio folder.

If sr is None, return audio_path. Else, return {audio_path}{sr}.

Parameters:	sr : int or None, optional Sampling rate.
Returns:	audio_path : str Path to the root audio folder. e.g. DATASET_PATH/audio subfolders : list of str List of subfolders include in audio folder. Important when use AugmentedDataset. e.g. [‘{DATASET_PATH}/audio/original’]

set_as_downloaded()¶: Saves a download.txt file in dataset_path as a downloaded flag.