Manuel Pariente (@mnlpariente) profile picture

Co-founder @Pulse_audition | PhD @Inria_Nancy Creator of Asteroid (https://teapaw.org/t.co/771BOSSUiH). Speech processing | embedded AI

Pulse Audition, France
Joined August 2011
Photo by Manuel Pariente (@mnlpariente)Photo by Manuel Pariente (@mnlpariente)Photo by Manuel Pariente (@mnlpariente)Photo by Manuel Pariente (@mnlpariente)Photo by Manuel Pariente (@mnlpariente)Photo by Manuel Pariente (@mnlpariente)Photo by Manuel Pariente (@mnlpariente)Photo by Manuel Pariente (@mnlpariente)Photo by Manuel Pariente (@mnlpariente)Photo by Manuel Pariente (@mnlpariente)
Next week I’m in Interspeech Rotterdam (17–21 Aug) 🤩 Let’s meet up if you’re into AI for audio and speech processing for hearing aids!
6
280
I'm looking for a talented ML Software Engineer to help our team scale and bring better speech intelligibility to people suffering from hearing loss ! Know anyone who might be interested ? Our team is in South of France 😍
3
9
653
I'm proud and thrilled to announce that @Pulse_audition has just been acquired by @EssiLux ! We'll keep on pushing the boundaries on embedded AI-based speech enhancement for hearing glasses to solve the social exclusion from which hearing impaired people suffer !
We are pleased to announce the acquisition of Pulse Audition, a French startup delivering AI-based noise reduction and voice enhancement through algorithms allowing people with hearing impairment to better understand speech, even in noisy environments. bit.ly/3DxZqG7
4
11
503
I'll be in San Fransisco most of next week 🌉 If you'd like to talk about the future of hearables, smart glasses, speech enhancement, or embedded AI in audio, shoot me a message, and I'd be glad to meet !
6
391
Would you pay for #pyannote custom or premium models? #AskingForAFriend (I'd appreciate a few ReTweets 🙏)
18%Yes
28%No
54%Show me the results
99 votes • Final results
6
27
1
14
6,426
Manuel Pariente retweeted
Listening test results and audio examples are out on the challenge website! Congratulations to the Northwestern Polytechnical University and ByteDance team for winning, and many thanks to all participants! We'll soon provide a further analysis of the results. @chimechallenge
The objective evaluation results for the CHiME-7 UDASE task are now available online! ➡️chimechallenge.org/current/t… The listening test 🎧 results will be released during the CHiME-2023 workshop at #INTERSPEECH2023 @chimechallenge @ISCAInterspeech
5
1
16
2,545
Working on semi-supervised learning or unsupervised domain adaptation for speech enhancement ? 🗣️🎙️🧠🔊 You might be interested in participating in the UDASE task of the CHiME-7 challenge ! For more information please visit chimechallenge.org/current/t…
The 7th CHiME Speech Separation and Recognition Challenge (CHiME-7) has been launched! Please check chimechallenge.org/
2
13
1,199
Manuel Pariente retweeted
🪩The @stateofai 2022 is live!🪩 In its 5th year, the #stateofai report condenses what you *need* to know in AI research, industry, safety, and politics. This open-access report is our contribution to the AI ecosystem. Here's my director's cut 🧵: stateof.ai
27
467
124
1,592
Manuel Pariente retweeted
5/ How to know what you're worth:
6
87
11
810
Manuel Pariente retweeted
Thread of DALL-E AI generated images and their prompts
63
918
415
3,525
Any community around audio in C++ you would recommend? Or one on real-time and low-power applications?
6
1
18
Great chart ! More related content on #inclusivity and #accessibility here: microsoft.com/design/inclusi…
This Post is from an account that no longer exists. Learn more
4
Belle initiative de vulgarisation de l'IA en Français 👏🇫🇷👏 Un plaisir d'y avoir contribué 🙏
🎙️L'effet "cocktail party" n'a rien à voir avec 🥂mais avec la capacité du🧠à réagir à votre prénom alors que vous écoutez qq1 vous parler à une soirée bruyante.Venez écouter @mnlpariente nous expliquer l'enjeu de l'#IA dans la séparation de source sonore. horizon-ia.com/saison-cockta…
1
7
Hey, my PhD thesis is public 🎉 The fifth chapter is published nowhere (yet) and might be interesting to some of you, phase-modeling people 🌊 "Implicit and explicit phase modeling in deep learning-based source separation" 👉 hal.inria.fr/tel-03395953
1
7
43
What's the cool way to learn Python and PyTorch from scratch nowadays? ➕ Bonus points if it can be done in the same time ➕ Drop it below 👇
2
6
I naively thought that I could apply that to mentor on Asteroid, to provide in-depth assistance to those in need. Instead, @CodementorIO considers that I'm not qualified to mentor on my own open-source toolkit 🤯 Can't say I was not surprised.
Yesterday, I was stuck at one open-source project issue for 2 hours and was still clueless. Surprisingly saw a GET HELP button 🤯 Signed up @CodementorIO, reached out to its main contributor, paid ~$80 for 50 minutes and it made my whole day 🥳
2
3
I released fast_bss_eval, a python package to compute SDR/SIR/SAR metrics for the evaluation of blind source separation algorithms! 1/4 pip install fast-bss-eval - numpy/torch ok #⃣🔥 - fast! 🚄 - GPU+differentiable 🎉 doc: fast-bss-eval.readthedocs.io… repo: github.com/fakufaku/fast_bss…
3
20
1
72
Manuel Pariente retweeted
Well... servers have emotions too!
2
6