Paper Title Number 3
Journal 1, 2015
This paper is about the number 3. The number 4 is left for future work.
Recommended citation: Your Name, You. (2015). "Paper Title Number 3." Journal 1. 1(3). http://academicpages.github.io/files/paper3.pdf
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Page Not Found
Page not found. Your pixels are in another canvas.
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
Meta-learning Extractors for Music Source Separation
Published:
This blog post is about the ICASSP 2020 paper Meta-Learning Extractors for Music Source Separation.1 I will summarise and comment on the main ideas.
Samuel, D., Ganeshan, A., & Naradowsky, J. “Meta-learning Extractors for Music Source Separation.” In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020. https://arxiv.org/abs/2002.07016 ↩
Interview with Romain Hennequin at ISMIR 2019
Published:
Romain Hennequin is a lead research scientist at Deezer working on music information retrieval. Prior to that, he was a researcher at Audionamix for three years. In 2011 he obtained a PhD from Télécom ParisTech for his work on musical spectrogram decomposition methods. I met him during the ISMIR conference 2019 in Delft and got the opportunity to talk with him about audio source separation.
Trends in Audio Source Separation - Insights from WASPAA 2019
Published:
I wrote this post together with my colleague Giorgia Cantisani. It has also been published on the MIP-Frontiers blog
Summer School DeepLearn 2019
Published:
At the end of July, I attended the 3rd International Summer School on Deep Learning, DeepLearn 2019 in Warsaw, Poland. It offered a full week of exciting talks, courses, networking and pirogi eating. In total there were 22 courses to choose from, which covered several aspects of deep learning research ranging from introductory to advanced levels. All speakers were well-known experts in their respective areas of research. Beyond that, three keynote talks and many presentations by participants about their work gave further insight into the extremely wide range of research fields where deep learning is applied. In this post, I will address some lessons I learnt at the summer school and briefly summarize some of my favorite courses.
publications
Weakly Informed Audio Source Separation
Kilian Schulze-Forster, Clement Doire, Gaël Richard, Roland Badeau
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2019
Deep learning based singing voice separation exploiting non-aligned side information with attention
Download here
Joint Phoneme Alignment and Text-Informed Speech Separation on Highly Corrupted Speech
Kilian Schulze-Forster, Clement Doire, Gaël Richard, Roland Badeau
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2020
Supervised speech separation with unsupervised phoneme level text-to-audio alignment
Download here
Phoneme Level Lyrics Alignment and Text-Informed Singing Voice Separation
Kilian Schulze-Forster, Clement Doire, Gaël Richard, Roland Badeau
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
Download here
Unsupervised Audio Source Separation Using Differentiable Parametric Source Models
Kilian Schulze-Forster, Clement Doire, Gaël Richard, Roland Badeau
ArXiv, 2022
Download here