If interested, check it out at arxiv.org/abs/2010.04506 Plus audio samples at github.com/tencentmusic/T…

Enjoyed this talk from @colinraffel at the first NLP 4 Music and Audio workshop. I completely agree with the punchline: we should be doing more transfer learning in MIR! youtube.com/watch?v=9ufD9W…

Tencent Music will exclusively host five-time Grammy Award-winning artist billie eilish’s livestreaming concert Where Do We Go? for fans in #China, free of charge. A special edition for China will be launched via #TMElive, on QQ Music, Kugou Music, Kuwo Music and WeSing. $TME

Check out our latest work! "Learning Audio Embeddings with User Listening Data for Content-based Music Recommendation" arxiv.org/abs/2010.15389 Work with my folks @Tencent_Music

This is probably as close to a 20th Birthday as we can get. Here's to 20 more years of open source multimedia! 🎉

QQ Music yearly wrap is out! This time we allow users to share a short video of 15 seconds to their social media. My folks and I did the function - which 15s is the best part to share as the BGM in the video🤘

Yay! Just accepted to #ICASSP2021

This is the story of how Bela ended up on stage with Snarky Puppy and on their Grammy Award winning album: Live at the Royal Albert Hall (Best Contemporary Instrumental Album)!! 🚀🚀🚀 Read all about it here: blog.bela.io/2021/03/15/sna… Steven Kruyswijk Snarky Puppy Bobby Sparks

After working 60h per week for 19 months, I left my job in TME. I am very proud of 9 models I landed in real products, 5 research papers I published, 3 patents I filed, and 2 interns I supervised. Will start working remotely for a startup and enjoy my work-life balance ☕️

This will be presented by Ke Chen at #ICASSP2021 MLSP-10 Deep Learning For Speech And Audio, 8 June 16:30-17:15. I will be around too 😉

Delighted to share our recent literature review on “Content-driven music recommender systems” with Markus Schedl Peter Knees and myself with the public: bit.ly/3BK0Ckh #music #recommender_system #MRS #ismir #content #onion_model ACM RecSys SIGIR 2025 ACM SIGIR @ismir2021

It has been quite a journey leaving my motherland 🇨🇳, reuniting with Manos in 🇬🇷, and starting our new life in 🇳🇴. Luckily, we managed to follow every travel regulation and nailed down residence permits. Still lots of paperworks ahead, but we’ll be fine💪

The last paper I did with my ex-colleagues is online: “Large-scale singer recognition using deep metric learning: an experimental study”. ieeexplore.ieee.org/abstract/docum…

Deep Learning Tools for Audacity: Helping Researchers Expand the Artist’s Toolkit abs: arxiv.org/abs/2110.13323 project page: interactiveaudiolab.github.io/project/audaci…

"The Sound of April", a short documentary presenting the soundbites during Shanghai's lockdown is being censored on Chinese social media, video accounts and Internet users collectively participate in saving and distributing videos as a form of protest against censorship.

``Supervised and Unsupervised Learning of Audio Representations for Music Understanding. (arXiv:2210.03799v1 [cs.SD]),'' Matthew C. McCallum, Filip Korzeniowski, Sergio Oramas, Fabien Gouyon, Andreas F. Ehmann, ift.tt/ADUkNIi

Had a great day attending #Brainstorm at #NTNU today! We presented our mission to the students and our research engineer, Dr. Beici Liang, had a great talk about music entity linking. #sparwk #ntnu #presentation #ntnubrainstorm #youdeservebetter #musictech #musictechnology

Frustrated to see the whole thread :(

“Why has our country come to this?” Mr. Zhang, who said that he grew up poor in a village, was grateful for the government’s assistance in his education. “I thought we would only move upward.” - Li Yuan袁莉⁩ on China’s first-time protesters. A must read. nytimes.com/2022/11/29/bus…

It has been so much fun serving as the Scientific Program Co-Chair for this year’s ISMIR Conference 🫶 Also super happy meeting up with my old and new friends in Milan #ISMIR2023. Hope to see you all again in the near future!