@faro@sigmoid.social Audio-AI researcher at @audioshakeai (Before: @inria, @FraunhoferIIS / @uniFAU). All in 17.68% of grey
Montpellier, France
Joined April 2008
- Tweets10K
- Following715
- Followers1K
- Likes845
Pinned Tweet
Happy to see that DeMask built with asteroid won the first place of the @PyTorch summer #hackathon!
The model allows you to enhance muffled speech when wearing facemask
Demo: youtu.be/QLf10Uqu8Yk
👋 to our team: @mnlpariente @michelolzam @_jonashaag and Samuel Cornell
I am looking for reviewers for a @JOSS_TheOJ submission with expertise in speech and python. The software under review is a new speech enhancement module of github.com/espnet/espnet (hence its so difficult to get reviewers without conflicts of interest). Any pointer is helpful!
The main author is github.com/neillu23 and paper submission can be found here: github.com/openjournals/joss…
260
Hey music separation researchers. We added a new definition of the SDR metric when we launched the last @sounddemix. To make it less confusing for future papers, we want to rename the metric. Please vote
32%TSNR
7%uSNR
11%NSDR
50%uSDR
28 votes • Final resultsDiscussion here: github.com/sigsep/sigsep-mus…
2
371
What a sad end.
I’ve never used the twitter app or their website for anything than a quick post and I won’t do that. Taking a break and waiting for #ivory
443
Finally!
Audio-based AI classifiers show no evidence of improved COVID-19 screening over simple symptoms checkers arxiv.org/abs/2212.08570
Great content at @ISMIRConf this year but I have to say that the hybrid format worked out worse than I had hoped. I wouldn’t attend hybrid again if it won’t have dedicated slots to meet people.
9
I am assigned to review #ICASSP2023 papers without having received an invitation. Is that how @ieeeICASSP fills in missing reviewers?
4
3
Brilliant paper!
🧠how does the brain process rapid speech-sound sequences?
💬how is auditory content maintained over time?
🧮how is temporal order encoded using an evolving spatial pattern?
for answers, see our latest paper! nature.com/articles/s41467-0… @JeanRemiKing @davidpoeppel @AlecMarantz
8
@nedwards just saw your article on airtags for tracking luggage... maybe worth adding some notes on airline regulations? arstechnica.com/gadgets/2022…
Excellent intro to scientific audio in python!
Videos from this year's @europython are up, including my talk on Working with Audio in Python!
Check it out if you're interested in, well, working with audio in Python - or if you're just curious how audio software works from the ground up. youtube.com/watch?v=NYhkqXpF…
5
@StabilityAI is the new @OpenAI
"Company StabilityAI has requested a takedown of this published model characterizing it as a leak of their IP"
Interesting....I thought StabilityAI stood for a decentralized push for AI.
So this move surprises me (even though they later retracted it).
huggingface.co/runwayml/stab…
1
1
@waxpancake it also happens in audio teapawt.net/regularbass/status/157…
Did you license these sounds for this purpose? For example, PSE expressly prohibits using our sounds in ML applications for generative sound (like this). The BBC remarc license does not contemplate this, and certainly doesnt allow for commercial use or redistribution of any kind
1
Looks like a new music separation SOTA model?
A very clever idea of splitting spectrogram into bands and apply RNN and achieve SDR=10dB on vocals! Music Source Separation with Band-split RNN arxiv.org/pdf/2209.15174.pdf
This is tinkering and engineering with open source tools (which is great) but not „an explosion of creativity“.
🔥New Video🔥Stable Diffusion has been released and is riding a wave of creativity and collaboration. But not everyone is happy about this. This video takes a look at the vibrant open-source community around the model, and its critics. Watch here:
youtu.be/xbxe-x6wvRw
ALT Unlimited Creativity
2
1