Pedro Sarmento
@umpedronosapato.bsky.social
📤 274
📥 343
📝 39
AI & Music Data Scientist at
@Music.AI
| prev. @c4dm
can't get enough of guitar-MIR 🎸
add a skeleton here at some point
6 months ago
0
1
0
Really creative use of AI for video by
#meatdept
on this banger (non AI) release by
#igorrr
🤘
www.youtube.com/watch?v=rbkk...
loading . . .
Igorrr - ADHD (Official Video)
YouTube video by Metal Blade Records
https://www.youtube.com/watch?v=rbkkxqghGNo
7 months ago
0
1
0
Let us hear your AI-assisted bangers 🤘
add a skeleton here at some point
7 months ago
0
2
0
So many great works 🤘
add a skeleton here at some point
7 months ago
0
2
0
reposted by
Pedro Sarmento
C4DM at QMUL
7 months ago
An exciting novel contribution by our student
@jinhua-liang.bsky.social
, supervised by
@emmanouilb.bsky.social
add a skeleton here at some point
0
3
1
Good luck to all the titans submitting to
#ISMIR2025
🤘excited to see what this year's edition will bring 🎸
7 months ago
1
3
0
reposted by
Pedro Sarmento
Nigel Warburton
7 months ago
4’33, One Minute, and the copyright grab - my Everyday Philosophy column
@theneweuropean.bsky.social
www.theneweuropean.co.uk/nigel-warbur...
loading . . .
Everyday Philosophy: John Cage and the sound of silence
A collective called the 1000 Artists have followed in the composer’s footsteps by releasing a silent protest album
https://www.theneweuropean.co.uk/nigel-warburton-everyday-philosophy-the-sound-of-silence/
0
19
6
I'm running a paid study on guitar timbre transfer - it should take approximately 30min 🎸 If you're interested, please reach out via DM!
7 months ago
0
2
4
reposted by
Pedro Sarmento
Oriol (Uri) Nieto
8 months ago
I love how DiffRhythm keeps changing time signatures à la Dream Theater (ie, seemingly random). The vocals are in a quite deep uncanny valley, but the music sounds super good. And the audio prompting works really well! And all open source! Great job, titans <3
huggingface.co/spaces/ASLP-...
loading . . .
DiffRhythm - a Hugging Face Space by ASLP-lab
Blazingly Fast and Embarrassingly Simple Song Generation
https://huggingface.co/spaces/ASLP-lab/DiffRhythm
0
6
1
They're out 🤘
add a skeleton here at some point
8 months ago
0
3
0
reposted by
Pedro Sarmento
Scott H. Hawley
8 months ago
Video of
@stefanlattner.bsky.social
's talk at DMRN+19 is finally online: "Models of Musical Signals: Representation, Learning & Generation"
@c4dm.bsky.social
www.youtube.com/watch?v=ixHf...
loading . . .
Models of Musical Signals: Representation, Learning & Generation. Stefan Lattner (Sony SCL). DMRN+19
YouTube video by C4DM - Centre for Digital Music
https://www.youtube.com/watch?v=ixHfBPXSgzo
0
9
2
reposted by
Pedro Sarmento
Sander Dieleman
8 months ago
Great interview with
@jascha.sohldickstein.com
about diffusion models! This is the first in a series: similar interviews with Yang Song and yours truly will follow soon. (One of these is not like the others -- both of them basically invented the field, and I occasionally write a blog post 🥲)
loading . . .
History of Diffusion - Jascha Sohl-Dickstein
YouTube video by Bain Capital Ventures
https://www.youtube.com/watch?v=VpYNlHIHT7o
0
44
12
reposted by
Pedro Sarmento
8 months ago
exitpoints.bandcamp.com/album/you-ar...
Grab some albums on bandcamp today, support independent artists and Musicares!
loading . . .
You Are The Right Length, by Exit Points
10 track album
https://exitpoints.bandcamp.com/album/you-are-the-right-length
2
6
1
Very excited to share our latest work, the GigaMIDI dataset with > 1.4M files, published at
#TISMIR
🤘 It was a huge pleasure to collaborate with such a team of titans
transactions.ismir.net/articles/10....
loading . . .
The GigaMIDI Dataset with Features for Expressive Music Performance Detection | Transactions of the International Society for Music Information Retrieval
The Transactions of the International Society for Music Information Retrieval publishes novel scientific research in the field of music information retrieval (MIR), an interdisciplinary research area concerned with processing, analysing, organising and accessing music information. We welcome submissions from a wide range of disciplines, including computer science, musicology, cognitive science, library & information science and electrical engineering.TISMIR was established to complement the widely cited ISMIR conference proceedings and provide a vehicle for the dissemination of the highest quality and most substantial scientific research in MIR. TISMIR retains the Open Access model of the ISMIR Conference proceedings, providing rapid access, free of charge, to all journal content. In order to encourage reproducibility of the published research papers, we provide facilities for archiving the software and data used in the research. To avoid excessive cost to the authors or their institutions, TISMIR is published in electronic-only format.
https://transactions.ismir.net/articles/10.5334/tismir.203
8 months ago
0
12
3
reposted by
Pedro Sarmento
C4DM at QMUL
9 months ago
From the 25th February to 4th March 2025, two C4DM researchers will participate at the 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025). More info at:
www.c4dm.eecs.qmul.ac.uk/news/2025-02...
loading . . .
The following works were authored/coauthored by C4DM PhD students and academic staff:
https://www.c4dm.eecs.qmul.ac.uk/news/2025-02-05.C4DM-at_AAAI_2025/
0
6
3
this is pricelessly sad and great at the same time 🤘 Courtney LaPlante is such a titan
add a skeleton here at some point
9 months ago
1
1
0
reposted by
Pedro Sarmento
Yoshua Bengio
9 months ago
Today, we are publishing the first-ever International AI Safety Report, backed by 30 countries and the OECD, UN, and EU. It summarises the state of the science on AI capabilities and risks, and how to mitigate those risks. 🧵 Full Report:
assets.publishing.service.gov.uk/media/679a0c...
1/21
loading . . .
7
255
126
Another banger 🤘
add a skeleton here at some point
9 months ago
0
0
0
Following up on the release of open source models that are shaking the AI status quo: YuE (乐) 🎵 - full music generation - demo: map-yue.github.io - conditioned on lyrics (even does vocal fry and growls 🤘) - Non-commercial license Super impressive and disruptive work!
github.com/multimodal-a...
loading . . .
GitHub - multimodal-art-projection/YuE: YuE: Open Full-song Generation Foundation Model, something similar to Suno.ai but open
YuE: Open Full-song Generation Foundation Model, something similar to Suno.ai but open - multimodal-art-projection/YuE
https://github.com/multimodal-art-projection/YuE
9 months ago
0
5
0
reposted by
Pedro Sarmento
Deezer Research
9 months ago
We are proudly engaged in improving transparency both for artists and users relative to the spread of AI generated music on our platform. Based on months of research we're deploying a large scale detector and aim to remove such content from our recommendations:
newsroom-deezer.com/2025/01/deez...
loading . . .
Deezer deploys cutting-edge AI detection tool for music streaming - Deezer Newsroom
Paris, January 24, 2025 – Deezer (Paris Euronext: DEEZR), the global music experiences platform has deployed a cutting-edge AI music detection tool, discovering that roughly 10,000 fully AI generated ...
https://newsroom-deezer.com/2025/01/deezer-deploys-cutting-edge-ai-detection-tool-for-music-streaming/
0
24
11
reposted by
Pedro Sarmento
AES AIMLA 2025
9 months ago
📢 Call for contributions: First AES International Conference on Artificial Intelligence and Machine Learning for Audio (AIMLA 2025), London, Sept. 8-10, 2025. More info:
aes2.org/contribution...
@c4dm.bsky.social
loading . . .
2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio Call for Contributions - AES
Submission Deadline: May 3, 2024
https://aes2.org/contributions/2025-1st-aes-international-conference-on-artificial-intelligence-and-machine-learning-for-audio-call-for-contributions/
0
6
3
reposted by
Pedro Sarmento
Scott H. Hawley
9 months ago
🎉 Follow-up: Thrilled to share that this tutorial has been accepted to
#ICLR2025
in the blog posts track!
add a skeleton here at some point
1
15
2
reposted by
Pedro Sarmento
arXiv Sound
9 months ago
AI-generated music detection achieved 99.8% accuracy using classifiers trained on real and artificial music. No details on methods or dataset size are provided.
loading . . .
AI-Generated Music Detection and its Challenges
Darius Afchar, Gabriel Meseguer-Brocal, Romain Hennequin
https://arxiv.org/abs/2501.10111
0
8
2
reposted by
Pedro Sarmento
Stefan Lattner
9 months ago
🎶✨ New Paper Announcement! ✨🎶 We present "Improving Musical Accompaniment Co-creation via Diffusion Transformers" 🎹🎸—a study advancing our Diff-A-Riff stem generator through improved quality, efficiency, and control. 📜Read the full paper here:
arxiv.org/pdf/2410.23005
🧵👇
loading . . .
https://arxiv.org/pdf/2410.23005
3
7
2
reposted by
Pedro Sarmento
Andrew McPherson
9 months ago
First Bsky post, first lab paper of 2025! "On mapping as a technoscientific practice in digital musical instruments" -- a dive on the history and critical implications of mapping theory, with speculation on possible futures. Forthcoming in JNMR:
instrumentslab.org/data/andrew/...
1
15
2
Let's go 🎸
add a skeleton here at some point
9 months ago
0
4
0
reposted by
Pedro Sarmento
Stephen Roddy
9 months ago
Russolo’s intonarumori are in the Guardian. We are so back.
www.theguardian.com/music/2025/j...
loading . . .
Play that funky noise intoner! The rumblers, gurglers and howlers of the world’s strangest orchestra
With their funnel-like hooters and cupboard-like shapes, they looked bizarre, sounded wild and left audiences baffled. Now, more than 100 years on, Luigi Russolo’s orchestra of futurist machine instru...
https://www.theguardian.com/music/2025/jan/16/noise-intoner-futurist-strangest-orchestra
0
20
5
reposted by
Pedro Sarmento
Marco Comunità
9 months ago
Help us with our research to: ☝️ - Develop a perceptual similarity metric for audio effects ✌️ - Advance the state of the art in audio effects modelling Take our listening test (<15min):
mcomunita.github.io/mushra-front...
Use: 💻 + 🎧 🙏
0
1
1
reposted by
Pedro Sarmento
Stefan Lattner
9 months ago
🧑🎓 Our
#ISMIR
Conference Tutorial "Deep Learning 101 for Audio-based MIR" provides a broad introduction to music audio processing, analysis, and generation. 📘 The book and jupyter notebooks:
geoffroypeeters.github.io/deeplearning...
🎥 The recording of the tutorial:
us02web.zoom.us/rec/share/Qz...
loading . . .
Deep Learning 101 for Audio-based MIR — Deep Learning 101 for Audio-based MIR
https://geoffroypeeters.github.io/deeplearning-101-audiomir_book/front.html
0
6
2
👀
add a skeleton here at some point
9 months ago
1
0
0
reposted by
Pedro Sarmento
Stefan Lattner
9 months ago
😃 Accepted
#ICASSP
papers of Sony CSL Music Team: Accompaniment Prompt Adherence: A Measure for Evaluating Music Accompaniment Systems M. Grachten, J. Nistal Estimating Musical Surprisal in Audio M. Bjare, G. Cantisani, S. Lattner and G. Widmer
2
8
1
reposted by
Pedro Sarmento
Jordi Pons
9 months ago
Weights are out! 🤗 Tokenizing 16kHz speech at very low bitrates. Inference code:
github.com/Stability-AI...
Model code:
github.com/Stability-AI...
Model weights:
huggingface.co/stabilityai/...
arXiv:
arxiv.org/abs/2411.19842
Audio demos:
stability-ai.github.io/stable-codec...
0
20
4
reposted by
Pedro Sarmento
Oriol (Uri) Nieto
9 months ago
By far, one of the best things of 2024:
www.youtube.com/watch?v=5hTM...
loading . . .
Gojira - Mea Culpa (Ah! Ça ira!) [OFFICIAL VIDEO]
YouTube video by Gojira
https://www.youtube.com/watch?v=5hTMYk7orHw
0
4
1
This is such an inspirational insight from Jorge Luis Borges 🙇♂️ super relevant today in our quest for more and more and more data
add a skeleton here at some point
9 months ago
0
1
1
reposted by
Pedro Sarmento
Alexandre Défossez
9 months ago
We just released the Helium-1 model , a 2B multi-lingual LLM which
@exgrv.bsky.social
and
@lmazare.bsky.social
have been crafting for us! Best model so far under 2.17B params on multi-lingual benchmarks 🇬🇧🇮🇹🇪🇸🇵🇹🇫🇷🇩🇪 On HF, under CC-BY licence:
huggingface.co/kyutai/heliu...
add a skeleton here at some point
0
25
8
reposted by
Pedro Sarmento
Jesse Engel
9 months ago
What an astonishingly tone deaf take. He misses the entire point of creative practice. Accessibility and mastery are not opposed, they're two ends of the same personal creative journey.
add a skeleton here at some point
1
6
1
reposted by
Pedro Sarmento
Vincent Lostanlen
9 months ago
I am organizing a session on "Advancements in Bird Communication Studies" at Forum Acusticum / Euronoise, to be held in Málaga on June 23–26, 2025. Please submit your abstract (max. 200 words) onto the conference portal before January 19th
www.fa-euronoise2025.org/abstract-sub...
loading . . .
Abstract submission - Forum Acusticum Euronoise 2025
Forum Acusticum Euronoise 2025
https://www.fa-euronoise2025.org/abstract-submission
0
6
2
reposted by
Pedro Sarmento
9 months ago
fixed - ismir2024 papers are accessible now! along with the reviews too, sometimes.
ismir2024program.ismir.net
add a skeleton here at some point
0
7
1
reposted by
Pedro Sarmento
Ethan Mollick
9 months ago
Interesting attempt to build an AI agent-based research assistant to automate machine learning paper writing by acting as PhDs, post-docs, & professors working in a typical lab. It doesn't autonomously produce high-level work but it looks promising as a copilot for researchers cutting cost & effort.
2
46
10
reposted by
Pedro Sarmento
QMUL School of Electronic Engineering and Computer Science
9 months ago
🤖 If you missed Prof. Shalom Lappin's insightful lectures series on the core ideas of his forthcoming book, 'Understanding
#AI
: Neither Catastrophe nor Redemption', you can catch up and watch the recordings on our Youtube channel:
www.youtube.com/@QMEECS/videos
0
2
1
Awesome DMRN
@c4dm.bsky.social
workshop today, with a great keynote by titan
@stefanlattner.bsky.social
and looooads of research around guitar 🤘🎸
@jackjamesloth.bsky.social
10 months ago
0
9
3
another banger work by titan
@hugofloresgarcia.bsky.social
🤘
add a skeleton here at some point
10 months ago
0
2
0
reposted by
Pedro Sarmento
Anil Ananthaswamy
10 months ago
The latest Science-in-Parallel episode dropped, in which I talk of this epochal moment in human history (the coming of LLMs), the 2024 NobelPrize for Hinton and Hopfield, and the history of neural networks, besides the writing of WHY MACHINES LEARN.
scienceinparallel.org/2024/12/anil...
loading . . .
Anil Ananthaswamy: AI's Nobel Moment - Science in Parallel
2024 was artificial intelligence’s Nobel Prize year with the physics and chemistry prizes recognizing the underpinnings and application of these […]
https://scienceinparallel.org/2024/12/anil-ananthaswamy-ais-nobel-moment/
0
11
2
reposted by
Pedro Sarmento
arXiv Sound
10 months ago
A deep learning pipeline uses spectrogram masking and the MuseScore API to separate instrument stems from music audio, convert them to MIDI, and transcribe them into sheet music.
loading . . .
Source Separation Automatic Transcription for Music
Bradford Derby, Lucas Dunker, Samarth Galchar, Shashank Jarmale, Akash Setti
https://arxiv.org/abs/2412.06703
0
1
1
reposted by
Pedro Sarmento
DCASE Challenge
10 months ago
The tasks for DCASE challenge 2025 have been announced.
dcase.community/articles/cha...
Stay tuned for more details.
loading . . .
Challenge tasks for DCASE2025 - DCASE
The DCASE Steering Group has reviewed the task proposals...
https://dcase.community/articles/challenge-tasks-for-dcase2025
0
7
5
reposted by
Pedro Sarmento
Anil Ananthaswamy
11 months ago
What? Linear algebra and calculus and machine learning for the holidays! Might a math-y book be a good gift for the holidays? I hope so :-) “A masterpiece.”-Geoff Hinton “A masterful work.”-Melanie Mitchell US
www.penguinrandomhouse.com/books/677608...
UK
www.penguin.co.uk/books/446849...
loading . . .
Why Machines Learn by Anil Ananthaswamy: 9780593185742 | PenguinRandomHouse.com: Books
A rich, narrative explanation of the mathematics that has brought us machine learning and the ongoing explosion of artificial intelligence Machine learning systems are making life-altering decisions...
https://penguinrandomhouse.com/books/677608/w…
0
14
2
reposted by
Pedro Sarmento
roser
11 months ago
📢 Call to all
#MIRCommunity
! Have you ever wondered what an open model means? Help us shape the definition of open models in generative AI for music by taking our survey — just 10 minutes! 👉
forms.gle/Z48t6HPBXwWC3r…
thank you 💫
loading . . .
https://forms.gle/Z48t6HPBXwWC3r…
0
3
2
join us 🤘
add a skeleton here at some point
11 months ago
1
1
0
reposted by
Pedro Sarmento
Sander Dieleman
11 months ago
There is a lot of great writing on flow matching out there all of a sudden! This post clarifies the connection with diffusion models -- they are essentially two different ways to describe the same class of models.
add a skeleton here at some point
0
27
3
reposted by
Pedro Sarmento
Scott H. Hawley
11 months ago
Thanks! BTW for anyone seeing this: I made my repo public (though still WIP) & would welcome feedback to improve the results:
github.com/drscotthawle...
e.g. 1. I haven't even added attention yet, and 2. I'm not sure the "GAN" part is really learning. Sample input/recon after 6 hours:
0
2
3
Load more
feeds!
log in