FaRo (@faroit) header
FaRo (@faroit) profile picture

FaRo

@faroit

@faro@sigmoid.social Audio-AI researcher at @audioshakeai (Before: @inria, @FraunhoferIIS / @uniFAU). All in 17.68% of grey

 Montpellier, France
faroit.com
Joined April 2008
  • Tweets10K
  • Following715
  • Followers1K
878Media
Photo by FaRo (@faroit)Photo by FaRo (@faroit)Photo by FaRo (@faroit)Photo by FaRo (@faroit)Photo by FaRo (@faroit)Photo by FaRo (@faroit)Photo by FaRo (@faroit)Photo by FaRo (@faroit)
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
5
22
DJs making music magic, create yours with AudioShake stems. djay Pro from @algoriddim now includes AudioShake’s tech to isolate vocals, instruments, and drums at the highest quality available to the industry. On mobile. 🎧📷#djtools #beatmaking
6
2
19
3,200
Our paper on lyrics transcription evaluation is on arXiv with updated and extended results (including Whisper v3)! 📄 arxiv.org/abs/2311.13987 Also, the benchmark is now on @paperswithcode: 🏆 paperswithcode.com/dataset/j… 👏 @faroit @h_schreiber @Luke_Miner @cnst_ant @AudioShakeAI
Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark

Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark

Current automatic lyrics transcription (ALT) benchmarks focus exclusively on word content and ignore the finer nuances of written lyrics including formatting and punctuation, which leads to a...

arxiv.org
AudioShake (@AudioShakeAI) profile pictureAudioShake@AudioShakeAI29 Nov 2023
This month at #ISMIR2023, AudioShake’s Research team presented a new benchmark for automatic lyric transcription systems– one that accounts for the nuances of music. You can read more on their new paper on AudioShake: audioshake.ai/post/new-bench…
Image from AudioShake (@AudioShakeAI)
1
2
15
1,287
We just released Jam-ALT, a formatting- and punctuation-aware automatic lyrics transcription benchmark (based on the JamendoLyrics dataset) that follows music industry guidelines. 🧵 🔎 audioshake.github.io/jam-alt… 🤗 huggingface.co/datasets/audi… 🧑‍💻 github.com/audioshake/alt-ev…

Jam-ALT: A Readability-Aware Lyrics Transcription Benchmark

audioshake.github.io
1
7
18
1,593
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!
GitHub - espnet/espnet: End-to-End Speech Processing Toolkit

GitHub - espnet/espnet: End-to-End Speech Processing Toolkit

End-to-End Speech Processing Toolkit. Contribute to espnet/espnet development by creating an account on GitHub.

github.com
1
1
9
1,220
The main author is github.com/neillu23 and paper submission can be found here: github.com/openjournals/joss…
neillu23 - Overview

neillu23 - Overview

neillu23 has 22 repositories available. Follow their code on GitHub.

github.com
260
Join us for a special edition of our Mila Music + AI Reading Group from February 8th to 22nd! We're excited to host 5 teams from the 2022 AI Song Contest, an international contest where musicians and scientists collaborate to explore human-ai co-creativity.
Image from Yusong Wu (@wuyusongwys)
1
10
1
56
14,111
#Pytorch implementation of MusicLM, new SOTA model for music generation using attention networks plus embeddings from MuLan, a text-audio contrastive learned model github.com/lucidrains/musicl…
3
7
586
🎻 The SDX23 challenge introduces a new formulation of audio source separation: cinematic sound separation. The task is to separate a movie's audio into three tracks: dialogue, sound effects & music. 📕 Give it a try using the starter kit. aicrowd.com/challenges/sound…
AIcrowd | Cinematic Sound Demixing Track - CDX'23 | Challenges

AIcrowd | Cinematic Sound Demixing Track - CDX'23 | Challenges

Source separation of a cinematic audio track into dialogue, sound-effects and misc.

aicrowd.com
1
3
5
1,119
#AudioLDM, the text-to-audio model, is now available on HuggingFace and GitHub to play with! We will add more functionality and further improve the model performance in the near future. Share the interesting samples you generate! github.com/haoheliu/AudioLDM huggingface.co/spaces/haohel…
GitHub - haoheliu/AudioLDM: AudioLDM: Generate speech, sound effects, music and beyond, with text.

GitHub - haoheliu/AudioLDM: AudioLDM: Generate speech, sound effects, music and beyond, with text.

AudioLDM: Generate speech, sound effects, music and beyond, with text. - haoheliu/AudioLDM

github.com
18
91
16
468
146,649
I guess developers are thrilled!
Developers (@XDevelopers) profile pictureDevelopers
@XDevelopers2 Feb 2023
Starting February 9, we will no longer support free access to the Twitter API, both v2 and v1.1. A paid basic tier will be available instead 🧵
1
303
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 results
3
1
1
8
1,945
Discussion here: github.com/sigsep/sigsep-mus…
add sdr metric from MDX challenge · Issue #89 · sigsep/sigsep-mus-eval

add sdr metric from MDX challenge · Issue #89 · sigsep/sigsep-mus-eval

we want to add the simplified SDR metric from the MDX challenge, and we realized that SDR isn't clear. So we are willing to rename the simplified metric: Please vote:

github.com
2
371
Lots of insights for ML researchers in this great interview with @colinraffel by @ellieevsss @forai_ml Some highlights: We're in the dark ages of ML model development. How can we build models collaboratively like we build open-source software? youtube.com/watch?v=fDUXSoFS… -1-
2
8
65
12,563
After 16 years, Twitterrific is discontinued: killed by an unannounced and undocumented policy change from a company no developer should ever trust again blog.iconfactory.com/2023/01…
2
7
614
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
Mysk 🇨🇦🇩🇪 (@mysk_co) profile pictureMysk 🇨🇦🇩🇪
@mysk_co15 Jan 2023
This is a proof that #Twitter has deliberately suspended @tweetbot. The developers just created a new Twitter API app and obtained new credentials. The app works, albeit with limits. Twitter API is not broken. If a platform pushes devs to resort to such workarounds, it's doomed
443
Diffusion Transformers (DiTs) are a new class of latent diffusion models (LDM) based on the transformers, obtained replacing the U-Net backbone with a transformer that operates on latent patches. DiTs are very similar to Vision Transformer (ViT) github.com/facebookresearch/…
GitHub - facebookresearch/DiT: Official PyTorch Implementation of "Scalable Diffusion Models with...

GitHub - facebookresearch/DiT: Official PyTorch Implementation of "Scalable Diffusion Models with...

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers" - facebookresearch/DiT

github.com
4
64
2
366
39,433
Chatbots are not a good replacement for search engines iai.tv/articles/all-knowing-…
All-knowing machines are a fantasy

All-knowing machines are a fantasy

The idea of an all-knowing computer program comes from science fiction and should stay there. Despite the seductive fluency of ChatGPT and other language models, they remain unsuitable as sources of...

iai.tv
16
136
24
508
218,639
A great read. Stop using the elbow criterion for k-means and how to choose the number of clusters instead (alternatives). "..researchers and reviewers should reject conclusions drawn from the elbow method." 📄 Paper: arxiv.org/abs/2212.12189
Image from Lior Alexander (@LiorOnAI)
26
257
25
1,229
194,198
FaRo retweeted
AK (@_akhaliq) profile picture
AK
@_akhaliq21 Dec 2022
A Length-Extrapolatable Transformer abs: arxiv.org/abs/2212.10554
Image from AK (@_akhaliq)
1
4
28
9,162
Load more