DSing ASR task: Resources and Baseline for an unaccompanied singing ASR.

DSing ASR task: Resources and Baseline for an unaccompanied singing ASR. In this repository, you will find the scripts used to construct the DSing ASR-oriented dataset and the baseline system constructed on Kaldi. Cite: <pre><code>@inproceedings{Roa_Dabike-Barker_2019, author = {Roa Dabike, Gerardo and Barker, Jon} title = {{Automatic Lyric Transcription from Karaoke Vocal Tracks: Resources and a Baseline System}}, year = 2019, booktitle = {Proceedings of the 20th Annual Conference of the International Speech Communication Association (INTERSPEECH 2019)} } </code></pre> 1- DSing dataset DSing is an ASR-oriented dataset constructed from the Smule Sing!300x30x2 dataset (<strong>Sing!</strong>). This repository provides the scripts to transform <strong>Sing!</strong> to the DSing ASR task. 2- Initial steps The first step before running any of the scripts is to obtain access to <strong>Sing!</strong> dataset. For more details, go to DAMP repository. 3- Transform Sing! to DSing dataset The scripts to transform the <strong>Sing!</strong> dataset to DSing ASR task dataset is located in the <strong>[DSing Construction](DSing Construction/)</strong> directory. The process is based on a series of python tools that are summarised in the runme_sing2dsing.sh bash script. Define the variable <em>version</em> with the name of the DSing version you want to construct (DSing1, DSing3 or DSing30). Any other option will raise an error. Set the variable <em>DSing_dest</em> with the path where the DSing version will be saved. Set the variable <em>SmuleSing_path</em> with the path to your copy of Smule Sing!300x30x2. Run code until step <strong>K</strong> ..... 4- Extract DSing dataset using pre-segmented data. If you want to do some analysis in the segmentation results or to use DSing for different porpoise than ASR. In directory <strong>[DSing preconstructed](DSing preconstructed)</strong> you can find a small script that allows recovering the transcriptions and utterance wav files. Just need to to set the output directory and the path of your version of <strong>Sing!</strong>