Pedro Sarmento
@umpedronosapato
Followers
3K
Following
19K
Media
134
Statuses
2K
AI & Music Data Scientist @moises_ai @wearemusicai | prev. @CDT_AI_Music @c4dm @QMUL
Joined June 2014
RT @hermanhwdong: 🔥Happy to announce that the AI for Music Workshop is coming to #NeurIPS2025!. We have an amazing lineup of speakers! We c….
0
44
0
RT @serrjoa: Who should be credited for this audio generation? In our recent work, we explore the application of unlearning methods to esta….
0
5
0
RT @zacknovack: I always like those paper/author visualizations for other conferences, so I ~vibe coded~ up an interactive one for #ISMIR20….
0
5
0
RT @howariou: ❌ We don’t need no negative samples.❌ We don’t need no large batches.❌ No modality gap in the classroom. Very happy to introd….
0
35
0
RT @Juj_Guinot: 🚨 Two papers at ISMIR 2025!. 🔹 SLAP: Siamese Language-Audio Pretraining 🔹GD-Retriever: Controllabl….
arxiv.org
Multimodal contrastive models have achieved strong performance in text-audio retrieval and zero-shot settings, but improving joint embedding spaces remains an active research area. Less attention...
0
4
0
RT @Ilaria__Manco: We’ve just released Magenta RealTime, an open-weights live music model that lets you craft sounds in real time by explor….
magenta.withgoogle.com
Magenta RealTimeToday, we’re happy to share a research preview of Magenta RealTime (Magenta RT), an open-weights live music model that allows you to interact...
0
19
0
RT @dorienherremans: Need to describe music as text? .🚀 Introducing 𝗦𝗼𝗻𝗶𝗰𝗩𝗲𝗿𝘀𝗲 🎶 An open-source framework for temporally aware music captio….
0
4
0
RT @CDT_AI_Music: 🎶 Excited to announce AIM’s presence at #IJCNN2025 in Rome! Our members @bhandari10k @plachouras @Juj_Guinot will presen….
0
3
0
👀.
Happy to say that our tutorial for Self-Supervised Learning in MIR was accepted @ISMIRConf 2025!! Join @howariou, @marco_ppasini @YuexuanKong, @Gabolsgabs and @deeplearnmusic, and myself in Daejeon in september to learn more about music SSL 🎶. Stay tuned for paper preprints 🎀.
0
0
6
😥.
Today I learned that the composer David Cope has died. He was the inventor of "Experiments in Musical Intelligence" (EMI), & visionary pioneer in computer-generated music. I wrote about his work in my 2019 book. I posted some excerpts from it in my blog: ⬇️.
0
0
1
RT @Yixiao_Zhang_: Instruct-MusicGen is accepted at ISMIR 2025 @ISMIRConf . Thanks to all collaborators and reviewers!.
0
12
0
RT @neutone_ai: Morpho v1.1.3 out now! 🦋. Some minor plugin improvements but we now support PayPal, Apple Pay, Google Pay and various other….
neutone.ai
Neutone Morpho is a realtime tone morphing plugin powered by advanced machine learning technology. Input sounds are resynthesized into a totally different style whilst keeping the overall shape of...
0
4
0
RT @loubbrad: Small teaser for our piano generative model -- enabling real time human-AI co-creation 🎹✨
0
4
0
RT @dadabots: Electrified Cicadas Play Pachobel’s Canon - “. enables us to make musics made from combinations of computer and insects”.http….
arxiv.org
We propose "Insect-Computer Hybrid Speaker", which enables us to make musics made from combinations of computer and insects. Lots of studies have proposed methods and interfaces for controlling...
0
2
0
Awesome work!.
🎶Introducing Moonbeam🌕: a foundation model for symbolic music, pretrained on 81.6K+ hours of diverse MIDI data across different instruments, genres and formats (e.g., performance and score MIDI)
0
0
3
RT @nicolasguozixun: 🎶Introducing Moonbeam🌕: a foundation model for symbolic music, pretrained on 81.6K+ hours of diverse MIDI data across….
0
20
0
RT @TeeJayBaker: Put together a neat little Max external for very quick and lightweight neural pitch estimation using @howariou's PESTO mod….
0
4
0
🤯🤯🤯.
🎶Now a neural network can read scanned score image and generate performance audio in end-to-end😎.I'm super excited to introduce our work on Unified Cross-modal translation between Score Image, Symbolic Music, and Audio. Why does it matter and how to make it? Check the thread🧵
0
0
3