Pedro Sarmento
@umpedronosapato.bsky.social
AI & Music Data Scientist at @Music.AI | prev. @c4dm
can't get enough of guitar-MIR 🎸
A new dataset (EGDB-PG) and a Tone-informed Transformer (TIT) model were developed for electric guitar transcription; TIT, trained on EGDB-PG, outperformed baselines across amplifier types due to dataset diversity and tone embedding; ablation studies assessed augmentation and embedding impact.
Towards Generalizability to Tone and Content Variations in the Transcription of Amplifier Rendered Electric Guitar Audio
Yu-Hua Chen, Yuan-Chiao Cheng, Yen-Tung Yeh, Jui-Te Wu, Jyh-Shing Roger Jang, Yi-Hsuan Yang
arxiv.org
April 11, 2025 at 5:30 PM
can't get enough of guitar-MIR 🎸
Really creative use of AI for video by #meatdept on this banger (non AI) release by #igorrr 🤘
www.youtube.com/watch?v=rbkk...
www.youtube.com/watch?v=rbkk...
Igorrr - ADHD (Official Video)
YouTube video by Metal Blade Records
www.youtube.com
April 3, 2025 at 5:28 PM
Really creative use of AI for video by #meatdept on this banger (non AI) release by #igorrr 🤘
www.youtube.com/watch?v=rbkk...
www.youtube.com/watch?v=rbkk...
Let us hear your AI-assisted bangers 🤘
🎶✨ AI Song Contest 2025 is HERE! ✨🎶
Are you ready to push the boundaries of music and AI?
🌍 Over 70 teams from 20+ countries have already redefined the future of music. Will YOU be next?
🔗 Learn more & sign up at www.aisongcontest.com
#AISongContest #AIinMusic #MusicInnovation #AISongContest2025
Are you ready to push the boundaries of music and AI?
🌍 Over 70 teams from 20+ countries have already redefined the future of music. Will YOU be next?
🔗 Learn more & sign up at www.aisongcontest.com
#AISongContest #AIinMusic #MusicInnovation #AISongContest2025
AI Song Contest
The AI Song Contest is an international competition exploring how humans can make music in collaboration with artificial intelligence
www.aisongcontest.com
March 28, 2025 at 12:25 PM
Let us hear your AI-assisted bangers 🤘
So many great works 🤘
We are very thrilled to share our contributions to this year's ICASSP - 14 papers!
For a list of the articles, please refer to:
www.c4dm.eecs.qmul.ac.uk/news/2025-03...
For a list of the articles, please refer to:
www.c4dm.eecs.qmul.ac.uk/news/2025-03...
As in previous years, the Centre for Digital Music will have a strong presence at the conference, both in terms of numbers and overall impact. The below papers authored or co-authored by C4DM members will be presented at the main ICASSP 2025 track:
www.c4dm.eecs.qmul.ac.uk
March 25, 2025 at 11:31 AM
So many great works 🤘
Reposted by Pedro Sarmento
An exciting novel contribution by our student @jinhua-liang.bsky.social, supervised by @emmanouilb.bsky.social
Exciting research update! EECS PhD students have developed a novel approach that enables large language models (LLMs) to “hear” and “understand” sound - a breakthrough in multimodal generative #AI: www.qmul.ac.uk/eecs/news-an...
EECS PhD researcher pioneers AI that can
www.qmul.ac.uk
March 22, 2025 at 6:43 PM
An exciting novel contribution by our student @jinhua-liang.bsky.social, supervised by @emmanouilb.bsky.social
Good luck to all the titans submitting to #ISMIR2025 🤘excited to see what this year's edition will bring 🎸
March 21, 2025 at 5:56 PM
Good luck to all the titans submitting to #ISMIR2025 🤘excited to see what this year's edition will bring 🎸
Reposted by Pedro Sarmento
4’33, One Minute, and the copyright grab - my Everyday Philosophy column @theneweuropean.bsky.social www.theneweuropean.co.uk/nigel-warbur...
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
www.theneweuropean.co.uk
March 11, 2025 at 8:22 AM
4’33, One Minute, and the copyright grab - my Everyday Philosophy column @theneweuropean.bsky.social www.theneweuropean.co.uk/nigel-warbur...
I'm running a paid study on guitar timbre transfer - it should take approximately 30min 🎸
If you're interested, please reach out via DM!
If you're interested, please reach out via DM!
March 10, 2025 at 10:03 AM
I'm running a paid study on guitar timbre transfer - it should take approximately 30min 🎸
If you're interested, please reach out via DM!
If you're interested, please reach out via DM!
Reposted by Pedro Sarmento
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-...
DiffRhythm - a Hugging Face Space by ASLP-lab
Blazingly Fast and Embarrassingly Simple Song Generation
huggingface.co
March 4, 2025 at 6:26 PM
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-...
They're out 🤘
ISMIR 2024 Conference Proceedings are now online! ismir.net/conferences/...
Thank you to all of the authors, reviewers, meta-reviewers, and conference organizers for their contributions to a vibrant and innovative research community!
#ISMIR2024 #MIR #Music #Research
Thank you to all of the authors, reviewers, meta-reviewers, and conference organizers for their contributions to a vibrant and innovative research community!
#ISMIR2024 #MIR #Music #Research
February 22, 2025 at 7:41 AM
They're out 🤘
Reposted by Pedro Sarmento
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...
"Models of Musical Signals: Representation, Learning & Generation" @c4dm.bsky.social
www.youtube.com/watch?v=ixHf...
Models of Musical Signals: Representation, Learning & Generation. Stefan Lattner (Sony SCL). DMRN+19
YouTube video by C4DM - Centre for Digital Music
www.youtube.com
February 12, 2025 at 3:47 AM
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...
"Models of Musical Signals: Representation, Learning & Generation" @c4dm.bsky.social
www.youtube.com/watch?v=ixHf...
Reposted by Pedro Sarmento
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 🥲)
(One of these is not like the others -- both of them basically invented the field, and I occasionally write a blog post 🥲)
History of Diffusion - Jascha Sohl-Dickstein
YouTube video by Bain Capital Ventures
www.youtube.com
February 10, 2025 at 10:28 PM
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 🥲)
(One of these is not like the others -- both of them basically invented the field, and I occasionally write a blog post 🥲)
Reposted by Pedro Sarmento
exitpoints.bandcamp.com/album/you-ar...
Grab some albums on bandcamp today, support independent artists and Musicares!
Grab some albums on bandcamp today, support independent artists and Musicares!
You Are The Right Length, by Exit Points
10 track album
exitpoints.bandcamp.com
February 7, 2025 at 5:58 PM
exitpoints.bandcamp.com/album/you-ar...
Grab some albums on bandcamp today, support independent artists and Musicares!
Grab some albums on bandcamp today, support independent artists and Musicares!
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....
transactions.ismir.net/articles/10....
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.
transactions.ismir.net
February 7, 2025 at 4:39 PM
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....
transactions.ismir.net/articles/10....
Reposted by Pedro Sarmento
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...
www.c4dm.eecs.qmul.ac.uk/news/2025-02...
The following works were authored/coauthored by C4DM PhD students and academic staff:
www.c4dm.eecs.qmul.ac.uk
February 5, 2025 at 4:28 PM
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...
www.c4dm.eecs.qmul.ac.uk/news/2025-02...
this is pricelessly sad and great at the same time 🤘 Courtney LaPlante is such a titan
Interviewer Mistakes SPIRITBOX's COURTNEY LAPLANTE For POPPY On The GRAMMYs Red Carpet, Does An Entirely Wrong Interview metalinjection.net/news/intervi...
Interviewer Mistakes SPIRITBOX's COURTNEY LAPLANTE For POPPY On The GRAMMYs Red Carpet, Does An Entirely Wrong Interview
This is hilarious.
metalinjection.net
February 3, 2025 at 2:42 PM
this is pricelessly sad and great at the same time 🤘 Courtney LaPlante is such a titan
Reposted by Pedro Sarmento
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
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
January 29, 2025 at 1:50 PM
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
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
Another banger 🤘
The Illustrated DeepSeek-R1
Spent the weekend reading the paper and sorting through the intuitions. Here's a visual guide and the main intuitions to understand the model and the process that created it.
newsletter.languagemodels.co/p/the-illust...
Spent the weekend reading the paper and sorting through the intuitions. Here's a visual guide and the main intuitions to understand the model and the process that created it.
newsletter.languagemodels.co/p/the-illust...
January 28, 2025 at 12:28 PM
Another banger 🤘
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...
- 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...
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
github.com
January 28, 2025 at 10:36 AM
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...
- 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...
Reposted by Pedro Sarmento
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...
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 ...
newsroom-deezer.com
January 27, 2025 at 9:04 AM
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...
Reposted by Pedro Sarmento
📢 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
More info: aes2.org/contribution...
@c4dm.bsky.social
2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio Call for Contributions - AES
Submission Deadline: May 3, 2024
aes2.org
January 27, 2025 at 12:16 PM
📢 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
More info: aes2.org/contribution...
@c4dm.bsky.social
Reposted by Pedro Sarmento
🎉 Follow-up: Thrilled to share that this tutorial has been accepted to #ICLR2025 in the blog posts track!
This blog post by @drscotthawley.bsky.social provides a very accessible overview of flow matching / rectified flow and reflow, based on intuitions from physics, rather than starting from probability distributions. The visualisations and animations are excellent, and the whole thing is also a colab!
blog - Flow With What You Know
Basic physics provides a “straight, fast” way to get up to speed with flow-based generative models
drscotthawley.github.io
January 23, 2025 at 1:47 PM
🎉 Follow-up: Thrilled to share that this tutorial has been accepted to #ICLR2025 in the blog posts track!
Reposted by Pedro Sarmento
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.
AI-Generated Music Detection and its Challenges
Darius Afchar, Gabriel Meseguer-Brocal, Romain Hennequin
arxiv.org
January 20, 2025 at 9:37 AM
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.
Reposted by Pedro Sarmento
🎶✨ 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 🧵👇
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 🧵👇
arxiv.org
January 20, 2025 at 1:42 PM
🎶✨ 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 🧵👇
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 🧵👇
Reposted by Pedro Sarmento
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/...
January 19, 2025 at 12:36 AM
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/...