SPLEETER: A FAST AND STATE-OF-THE ART MUSIC SOURCE SEPARATION TOOL WITH PRE-TRAINED MODELS

By Romain Hennequin, Anis Khlif, Félix Voituret, Manuel Moussallam. 2019

Subfields: Generative Models, Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

1. Heewoo Jun
2. Ilya Sutskever
3. Prafulla Dhariwal
4. Stefano Ermon
5. Alec Radford
6. Jonathan Ho
7. Yoshua Bengio
8. Christine Payne

In Speech & Audio

1. Christine Payne
2. Ilya Sutskever
3. Jong Wook Kim
4. Yuki Mitsufuji
5. Heewoo Jun
6. Alec Radford
7. Naoya Takahashi
8. Prafulla Dhariwal

Citations in the corpus

• Jukebox: A Generative Model for Music (2020, methodology): “To address this, we use Spleeter (Hennequin et al., 2019) to extract vo-cals from each song and run NUS AutoLyricsAlign (Gupta et al., 2020) on the extracted vocals to obtain a word-level alignments of the lyrics, allowing us to more accurately provide the lyrics for a given chunk of audio.”
• D3Net: Densely connected multidilated DenseNet for music source separation (2020, background): “Many types of neural network architecture have been proposed, including feedforward fully connected networks (FNNs) [1, 2], recurrent neural networks (RNNs) [3], convolutional neural networks (CNNs) [4–9] and their combinations [10,11].”