Eduardo Fonseca

184 posts

Eduardo Fonseca banner
Eduardo Fonseca

Eduardo Fonseca

@edfonseca_

Research Scientist @GoogleDeepMind. Sound Understanding. Previously @GoogleAI and @mtg_upf. He/him.

NYC Katılım Ekim 2017
565 Takip Edilen1.1K Takipçiler
Sabitlenmiş Tweet
Eduardo Fonseca
Eduardo Fonseca@edfonseca_·
🔊New paper! Recomposer allows editing sound events within complex scenes based on textual descriptions and event roll representations. And we discuss the details that matter! Work led by Dan Ellis w/ a bunch of Sound Understanding folks @GoogleDeepMind arxiv.org/abs/2509.05256
Eduardo Fonseca tweet media
English
0
4
42
5.8K
Eduardo Fonseca retweetledi
Vivek Kumar
Vivek Kumar@vivek_kumar·
Excited to share our work from Sound Understanding team at @GoogleDeepMind! Ever wanted to remove a single cough from a recording or make a faint doorbell louder? Recomposer makes editing complex audio scenes possible! Paper: arxiv.org/abs/2509.05256 #AudioEditing #GenerativeAI
Eduardo Fonseca@edfonseca_

🔊New paper! Recomposer allows editing sound events within complex scenes based on textual descriptions and event roll representations. And we discuss the details that matter! Work led by Dan Ellis w/ a bunch of Sound Understanding folks @GoogleDeepMind arxiv.org/abs/2509.05256

English
1
5
24
3.7K
Eduardo Fonseca retweetledi
arXiv Sound
arXiv Sound@ArxivSound·
Daniel P. W. Ellis, Eduardo Fonseca, Ron J. Weiss, Kevin Wilson, Scott Wisdom, Hakan Erdogan, John R. Hershey, Aren Jansen, R. Channing Moore, Manoj Plakal, "Recomposer: Event-roll-guided generative audio editing," arxiv.org/abs/2509.05256
English
0
7
23
2.4K
Eduardo Fonseca retweetledi
Annamaria Mesaros
Annamaria Mesaros@AnnamariaMsros·
I'm looking for a PhD student to work on continual learning for audio. Funding available for 2 years to start with, to be extended to 4 later. Contact me through email if interested! If you participated to @DCASE_Challenge or are coming to @DCASE_Workshop even better!
English
3
32
112
15.3K
Eduardo Fonseca retweetledi
Vivek Kumar
Vivek Kumar@vivek_kumar·
It's so awesome to see the impact of the computational audio capabilities we developed featured in @madebygoogle 🎉 🎉 🎉 Congrats to John Hershey, @ScottTWisdom, @PGetreuer & everyone who contributed for pioneering new computational audio capabilities in Pixel8 #MadeByGoogle
Google Photos@googlephotos

Check out the 4 new Google Photos features coming first to Pixel 8 and 8 Pro ↓ Whether it’s noise from wind, traffic, or barking dogs, Audio Magic Eraser in Google Photos reduces distracting sounds in your video in just a few taps! 🪄

English
4
16
60
20.3K
Eduardo Fonseca
Eduardo Fonseca@edfonseca_·
🔊New paper out: Do you use data balancing in your AudioSet experiments? It gets you a little mAP boost? It might work differently than you think...😅 You might want to check our last paper, led by @ChannningMoore
Eduardo Fonseca tweet media
Channing Moore@ChannningMoore

Our 2023 ICASSP paper is now up on arXiv: Dataset balancing can hurt model performance arxiv.org/abs/2307.00079 Dataset balancing works differently than you might assume: - can cause overfitting; - doesn’t improve performance on rare classes; - speeds up training convergence.

English
0
1
16
2.3K
Eduardo Fonseca
Eduardo Fonseca@edfonseca_·
Not sure my reviews were that "outstanding"... 😅, but the recognition is nice...  Thanks to the @ieeeICASSP committee.  #ICASSP2023
Eduardo Fonseca tweet media
English
0
0
27
1.9K
Eduardo Fonseca retweetledi
Annamaria Mesaros
Annamaria Mesaros@AnnamariaMsros·
📢 The countdown to DCASE Challenge 2023 deadline is on! 🗓️ Deadlines: * System submission: 15/5 - 23.59 AoE * Technical reports: 22/5 - 23.59 AoE
English
0
2
6
999
Magdalena Fuentes
Magdalena Fuentes@mfu3ntes·
Exciting life update‼️ Today I started as Assistant Professor of Music Technology and Integrated Design & Media 📚💻 at @nyusteinhardt and @nyutandon, within the wonderful @nyuMARL and @IdmNyu. If you're interested to work with me, reach out! 📬 🗽
English
16
2
99
0
Eduardo Fonseca
Eduardo Fonseca@edfonseca_·
Aaand that was after defending my PhD thesis some months ago "Training Sound Event Classifiers Using Different Types of Supervision" & taking some time off :) Thesis/video/slides & a quick summary available here: eduardofonseca.net/thesis/2022/01… SUPER thankful to all @mtg_upf folks!!🙌
English
0
0
13
0
Eduardo Fonseca retweetledi
HEAR Benchmark
HEAR Benchmark@hearbenchmark·
HEAR PMLR journal submissions are open until 2022-06-30. neuralaudio.ai/hear2021-pmlr.… Besides that, people have asked if they can run HEAR benchmarks, get on the leaderboard, cite us in the future. Yes! HEAR is here to stay. See our updated website: neuralaudio.ai
English
0
5
17
0
Eduardo Fonseca retweetledi
Romain Serizel
Romain Serizel@RSerizel·
📣 We have a (super cool) PhD position in speech enhancement for patients with auditory neuropathy spectrum disorders. If you're interested in Audio Signal Processing/MAchine Learning/Audiology, contact us! More info ⤵️ #version" target="_blank" rel="nofollow noopener">adum.fr/as/ed/voirprop…
English
1
10
14
0
daisukelab
daisukelab@nizumical·
We used MAE with spectrogram input, evaluated the HEAR 2021 benchmark, and visualized reconstructions and self-attention maps to understand learned features. (I like visualizations.♥)
daisukelab tweet mediadaisukelab tweet media
English
2
0
4
0
Eduardo Fonseca retweetledi
daisukelab
daisukelab@nizumical·
Our new paper is out! We explored a simple masked patch modeling w/o augmentation to learn a latent that describes the input spectrogram as it is. “Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation” arxiv.org/abs/2204.12260
English
2
2
29
0

Keşfet

@nizumical @kwmrtko @tkawamu24449159 @tmu_onolab @GoogleDeepMind @DCASE_Challenge @DCASE_Workshop @anuragarnab