Sign in

Faro Stöter

@faroit.bsky.social
230 followers 267 following 27 posts

AudioML research scientist at audioshake.ai, before: post-doc @inria@social.numerique.gouv.fr, Editor at bsky.app/profile/joss-openjournals.… All in 17.68% of grey, located in Frankfurt (Germany)

PostsRepliesMedia
Faro Stöter @faroit.bsky.social · 21/08/2025
Enjoyed my first @interspeech.bsky.social conference. Seems like a great community. Well organized and great venue. This is how big conferences could look like. Take notes, ICASSP!
020
Faro Stöter @faroit.bsky.social · 17/08/2025
Now in Rotterdam at @interspeech.bsky.social with @cifkao.bsky.social and @hschreiber.bsky.social
000
Reposted by Faro Stöter
Scott H. Hawley @drscotthawley.bsky.social · 20/03/2025
Harvard Business on Open Source: When PyTorch left Meta for its own non-profit, "this shift led to a significant decrease in contributions from Meta but a notable increase from external companies...participation increased from complementors (Chip Manufacturers);" papers.ssrn.com/sol3/papers....
papers.ssrn.com
Igniting Innovation: Evidence from PyTorch on Technology Control in Open Collaboration
<div> Many companies offer free access to their technology to encourage outside add-on <span>innovation, hoping to later profit by raising prices or harne
041
Faro Stöter @faroit.bsky.social · 25/06/2025
🚀 We’re looking for a Master’s student to join our research team for a 6-month internship at AudioShake! Deep dive into PyTorch, optimize our SOTA audio models, and help make ML sound better (and faster) 🎶 Based in Paris or remote 🇫🇷 → audioshake.notion.site/Internship-M... #AudioML #Internship
audioshake.notion.site
Internship: ML Optimization | Notion
Location: Paris preferred (remote within France/EU possible)
013
Reposted by Faro Stöter
siddhant-arora.bsky.social @siddhant-arora.bsky.social · 05/03/2025
🚀 New #ICLR2025 Paper Alert! 🚀 Can Audio Foundation Models like Moshi and GPT-4o truly engage in natural conversations? 🗣️🔊 We benchmark their turn-taking abilities and uncover major gaps in conversational AI. 🧵👇 📜: arxiv.org/abs/2503.01174
196
Faro Stöter @faroit.bsky.social · 20/05/2025
@interspeech.bsky.social new to the speech community coming from ISMIR/ICASSP/Eusipco/DAFX. How come Interspeech is that much more expensive than other conferences? This makes it very hard for many researchers to get approval!
110
Faro Stöter @faroit.bsky.social · 04/04/2025
Not knowing much about spatial audio: how do people render multiple dry mono sources to a wet reverberated stereo image where each source has a fixed position in space? I guess one could use ambisonics RiRs to create stereo images? But whats the easier way to handle the positioning?
100
Reposted by Faro Stöter
AudioShake @audioshakeai.bsky.social · 05/03/2025
AudioShake’s Multi-Speaker Separation is the first-ever hi-res solution for isolating overlapping voices. Perfect for media pros, transcription, & AI voice workflows. 🔗www.audioshake.ai/post/introducing-multi-speaker-separation-from-audioshake
054
Reposted by Faro Stöter
AudioShake @audioshakeai.bsky.social · 13/02/2025
How stem separation tech brought the legendary voice of Maria Callas back to life in “Maria". 🎶 Isolating Callas’s original vocals allowed @warnerclassics.bsky.social and filmmakers to control and blend her voice with Jolie’s performance. 🔗 Read: www.audioshake.ai/post/audiosh...
audioshake.ai
AudioShake Isolations Bring Maria Callas’ Voice to Life in Netflix film, “Maria”
Filmmakers and Warner Classics in partnership with the Maria Callas Estate, used AudioShake’s stem separation to isolate her voice to perfect the biopic’s music
072
Reposted by Faro Stöter
Alexandre Défossez @honualx.bsky.social · 13/01/2025
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...
0258
Reposted by Faro Stöter
gerkmann.bsky.social @gerkmann.bsky.social · 06/01/2025
Our article, "Diffusion Models for Audio Restoration: A Review," is now published in the IEEE Signal Processing Magazine! A huge thank you to all co-authors Jean-Marie Lemercier, Julius Richter, Simon Welker, Eloi Moliner, and Vesa Välimäki for a great collaboration. doi.org/10.1109/MSP....
doi.org
Diffusion Models for Audio Restoration: A review [Special Issue On Model-Based and Data-Driven Audio Signal Processing]
With the development of audio playback devices and fast data transmission, the demand for high sound quality is rising for both entertainment and communications. In this quest for better sound quality...
0125
Reposted by Faro Stöter
Earth Species Project (ESP) @earthspecies.bsky.social · 05/12/2024
Today, we’re introducing NatureLM-audio: the first large audio-language model tailored for understanding animal sounds. arxiv.org/abs/2411.07186 🧵👇
2158
Faro Stöter @faroit.bsky.social · 27/12/2024
Where is AGI that charges all my devices and batteries?
000
Reposted by Faro Stöter
Marcely Zanon Boito @marcelyzboito.bsky.social · 21/11/2024
Since this is a new platform and mHuBERT-147 just reached 86k downloads, let me make some promotion! This year we released a compact powerful multilingual SSL model. Trained on balanced, high-quality, open-license data, this model rivals MMS-1B but is 10x smaller. huggingface.co/utter-projec...
huggingface.co
utter-project/mHuBERT-147 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
2153
Reposted by Faro Stöter
Oded Rechavi @odedrechavi.bsky.social · 11/12/2024
Looking for reviewers before Christmas
1167389
Reposted by Faro Stöter
Interspeech 2026 @interspeech.bsky.social · 06/12/2024
🌟 URGENT Challenge @ #Interspeech2025 🌟 Join the Universal, Robust, & Generalizable Speech EnhancemeNT (URGENT) challenge! Explore noisy corpora, tackle diverse speech degradations, and test scalability across 2 tracks (~2.5k/60k hrs). 🚀 Learn more: urgent-challenge.github.io/urgent2025/
interspeech2025.org challenge URGENT Organizers: Kohei Saijo, Wangyou Zhang, Samuele Cornell, Robin Scheibler, Chenda Li, Zhaoheng Ni, Anurag Kumar, Marvin Sach, Yihui Fu, Wei Wang, Tim Fingscheidt, Shinji Watanabe
064
Reposted by Faro Stöter
hugofloresgarcía @hugofloresgarcia.bsky.social · 12/12/2024
new paper! 🗣️Sketch2Sound💥 Sketch2Sound can create sounds from sonic imitations (i.e., a vocal imitation or a reference sound) via interpretable, time-varying control signals. paper: arxiv.org/abs/2412.08550 web: hugofloresgarcia.art/sketch2sound
2239
Reposted by Faro Stöter
Justin Salamon @justinsalamon.bsky.social · 09/12/2024
📢 Audio AI Job opportunity at Adobe! The Sound Design AI Group (SODA) is looking for an exceptional research engineer to join us in building the future of AI-assisted audio and video creation. Strong ML background, GenAI experience a plus. Details: adobe.wd5.myworkdayjobs.com/external_exp...
1113
Reposted by Faro Stöter
robinsch @fakufaku.bsky.social · 06/12/2024
🚨🚨My team @GoogleDeepMind in Tokyo is looking for a talented research scientist to work on audio generative models! 🔊 Please consider applying if you have expertise in the domain or related areas such as multimodal models, video generation 📹, etc. boards.greenhouse.io/deepmind/job...
boards.greenhouse.io
DeepMind
044
Faro Stöter @faroit.bsky.social · 07/12/2024
€700M and not even generative? Doesn’t seem like a good investment. www.theguardian.com/world/2024/n...
theguardian.com
Notre Dame reopening offers ‘shock of hope’, says Emmanuel Macron
French president tours medieval cathedral in Paris to view restoration after devastating 2019 fire
010
Reposted by Faro Stöter
Titouan "SpeechBrain" Parcollet @tparcollet.bsky.social · 01/12/2024
🎓Academia or the industry 💸? I wrote a detailed point of view on Twitter a few months ago, so maybe I should share it here again. I think that most things are still true, the only slight change would be linked to the GenAI bubble, but only time will tell. www.darnault-parcollet.fr/documents/Ba...
darnault-parcollet.fr
041
Reposted by Faro Stöter
hardmaru @hardmaru.bsky.social · 01/12/2024
The Reality for AI Startups
“My AI startups is just a GPT Wrapper”
513923
Reposted by Faro Stöter
Dave Karpf @davekarpf.bsky.social · 30/11/2024
Here’s the most charitable reading I can offer: The tech barons behaved as though they were atop a social hierarchy, and expected mass adoration for their generosity+forgiveness for mistakes. Instead, Elizabeth Warren, Lina Khan et al treated them like the heads of *massive corporations.*
Marc Andreessen
• • •
Big Tech spent a decade doing everything possible to be the best conceivable progressive ally. They got treated with utter contempt, pounded daily, crucified in return. A full rethinking is required.
22884271483
Reposted by Faro Stöter
yamakatz @kyama0321.bsky.social · 28/11/2024
🤖👂🎶 > Towards Improved Objective Perceptual Audio Quality Assessment -- Part 1: A Novel Data-Driven Cognitive Model arxiv.org/abs/2411.18222
arxiv.org
Towards Improved Objective Perceptual Audio Quality Assessment -- Part 1: A Novel Data-Driven Cognitive Model
Efficient audio quality assessment is vital for streamlining audio codec development. Objective assessment tools have been developed over time to algorithmically predict quality ratings from subjectiv...
041
Reposted by Faro Stöter
Kashyap Chitta @kashyap7x.bsky.social · 24/11/2024
For those of you who haven't yet, give scholar-inbox.com a try! It's a free personal paper recommender which helps you stay up-to-date by sending daily/weekly paper digests directly to your inbox. Your votes train your own classifier, and you can have a peek at its feature words. Here are mine!
2176
Reposted by Faro Stöter
Kris Kashtanova @kris.art · 27/11/2024
Introducing MultiFoley, a video-aware audio generation method with multimodal controls! 🎉 ⌨️Make a typewriter sound like a piano 🎹 🐱Make a cat meow like a lion roars! 🦁 ⏱️Perfectly time existing SFX 💥 to a video Link to research in comments: by Adobe Research
2405
Reposted by Faro Stöter
Sai Prasanna @saiprasanna.in · 26/11/2024
Arxiv sharing reminder pdf ❌ abs ✅
925141
Faro Stöter @faroit.bsky.social · 26/11/2024
Is there any Bluesky app that could just do the bare minimum of remembering the position in the timeline when closing? This is as bad as twitter was when I left years ago
110
Faro Stöter @faroit.bsky.social · 26/11/2024
Impressive list of tasks (including separation). Also they demo a MUSDB18 track in the demo, so I have to like it? blogs.nvidia.com/blog/fugatto-gen-a… www.youtube.com/watch?v=qj1Sp8He6e4
160
Reposted by Faro Stöter
François Fleuret @francois.fleuret.org · 26/11/2024
My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch. fleuret.org/dlc/ And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!) fleuret.org/lbdl/
461253247
Reposted by Faro Stöter
Jordi Pons @jordiponsdotme.bsky.social · 25/11/2024
3172
Reposted by Faro Stöter
Peter Chilvers @peterchilvers.com · 22/11/2024
I'm putting together a starter pack of audio developers, I'm finding it surprisingly hard to find them. Any suggestions welcome... go.bsky.app/TJykYAM
11158
Reposted by Faro Stöter
Paul McCabe | ROLAND @mccabep.bsky.social · 25/11/2024
My dear friend @pkirn.bsky.social has put together this Starter Pack which is worthy of a “Follow All”… go.bsky.app/JwEMgBH
162
Faro Stöter @faroit.bsky.social · 25/11/2024
Audio bandwidth extension (why do people call this super-resolution?) is making quite some progress! demo: aeromamba-super-resolution.github.io code: github.com/aeromamba-su...
0101
Faro Stöter @faroit.bsky.social · 25/11/2024
> Open-Amp can render audio online during training Sounds like a very interesting approach to training loops with realtime audio. Arxiv: arxiv.org/abs/2411.14972 Code: github.com/Alec-Wright/...
092
Reposted by Faro Stöter
keunwoochoi.bsky.social @keunwoochoi.bsky.social · 24/11/2024
#ismir2025 already has an website! isn't it crazy? ismir2025.ismir.net
ismir2025.ismir.net
ISMIR 2025
1145
Reposted by Faro Stöter
Jonathan Le Roux @jonathanleroux.bsky.social · 18/11/2024
I initiated a starter pack for Audio ML. Let me know if you'd like to be added/removed. go.bsky.app/LGmct4z
466822
Faro Stöter @faroit.bsky.social · 23/11/2024
I’m sad that mastodons failed to attract researchers. But mostly because I like the ivory for Mac and iOS. But let’s see if they add support at some point 🤞
010
Faro Stöter @faroit.bsky.social · 23/11/2024
@carlthome.bsky.social no way! My social media world is complete again! 😃
110
Faro Stöter @faroit.bsky.social · 23/11/2024
@jordiponsdotme.bsky.social hello hello. I was hoping you would all do mastodon but well… Looks like you found all audio folks already here. What about creating an audio science starter pack?
000
Reposted by Faro Stöter
Jonathan Le Roux @jonathanleroux.bsky.social · 23/11/2024
The #SANE2024 talks are up on YouTube! Feat. Quan Wang, @gretatuckute.bsky.social, Mark Hamilton, Bhuvana Ramabhadran, Zhiyao Duan, Chris Donahue. Binge watching playlist⬇️ youtube.com/playlist?lis...
youtube.com
SANE 2024 @ Google Cambridge - YouTube
SANE 2024, a one-day event gathering researchers and students in speech and audio from the Northeast of the American continent, was held on Thursday October ...
0176
Reposted by Faro Stöter
Sung Kim @sungkim.bsky.social · 30/10/2024
Google Deepmind's Pushing the frontiers of audio generation An overview of their latest speech generation research underpinning all of these products (both NotebookLM and Illuminate) and experimental tools. deepmind.google/discover/blo...
deepmind.google
Pushing the frontiers of audio generation
Our pioneering speech generation technologies are helping people around the world interact with more natural, conversational and intuitive digital assistants and AI tools.
073