i assumed pyannote would be made obsolete by cheap multimodal LLMs—turns out, i was completely wrong and an idiot

#frenchtech

French Tech : Pyannote, la start-up qui perfectionne l'IA vocale trib.al/oTGU5Bs

Go go go pyannoteAI, let's solve speaker diarization together! DMs are open! linkedin.com/posts/pyannote…

Glad to share this new study comparing the performance and biases of the LENA and ACLEW algorithms in analyzing language environments in Down, Fragile X, Angelman syndromes, and populations at elevated likelihood for autism 👶📄 osf.io/preprints/psya… 🧵1/12

From open-source dominance to enterprise transformation, pyannoteAI is redefining what’s possible in Voice AI. We're proud to lead their $9m Seed, supporting vincentmolina, Hervé "pyannote" Bredin and their mission to bring speaker intelligence to the forefront. Speaker diarisation isn’t

Read Morgane Zerath's post on why we backed this brilliant team - crane.vc/welcoming-pyan…

View from ⁦pyannoteAI⁩ Parisian HQ this morning 🥖

Pyannote : l'IA qui reconnaît les voix "La voix est notre vecteur de communication le plus riche, mais elle est inexploitée" 💬 Vincent Molina, cofondateur de Pyannote 🎙️ François Sorel

Does it do speaker diarization? 👀 pyannoteAI

github.com/pytorch/audio/… Torchaudio just announced it will be pure Python again. That means dropping efficient kernels like filter, RNN-Tranducer, etc. It's an unwise and disruptive decision tbh. If your work will be affected by this, please leave a comment there... PyTorch

It's a bit wild how challenging speaker diarization, especially in overlap speech, still is, even with all the talk about AGI. In the brain, vision is complex, audio is simpler. In computer, however, it seems the other way around. 😃

Looks like one of my favorite artist is trying to tell me something... dzr.page.link/buyQPzN9beuV1b…

📢 Join our Conversational AI Reading Group! 📅 Thursday, May 22nd | 11 AM - 12 PM EST 🎙 Speaker: Hervé Bredin (Hervé "pyannote" Bredin) 📖 Topic: "Speaker diarization, a (love) loss story" 🔗 Details: (poonehmousavi.github.io/rg)

... in which I'll talk about my decade-old love for speaker diarization and the loss functions used to train underlying neural networks

Polishing my slides right now :)

Learn about speaker diarization, the science behind it, and the future of diarization at ⁦pyannoteAI⁩ research labs youtu.be/ECqxZgVevuI?fe…

State-of-the-art pyannoteAI speaker diarization now runs natively on your iPhone, iPad, and MacBook! Looking forward to what you are going to build! Great collab with argmax !

Honored to partner with argmax A-team

Look ma! I am on your iPhone now! Great collab with argmax