Convai_rg (@convai2024) 's Twitter Profile
Convai_rg

@convai2024

ID: 1854237737630781440

linkhttps://poonehmousavi.github.io/rg calendar_today06-11-2024 19:01:57

22 Tweet

164 Followers

1 Following

Convai_rg (@convai2024) 's Twitter Profile Photo

πŸ“’ Join our Conversational AI Reading Group! πŸ“… Thursday, April 24th | 11 AM - 12 PM EST πŸŽ™ Speaker: Oriol Nieto(Oriol (Uri) Nieto) from Adobe Research πŸ“– Topic: "GenAI for Sound Design" πŸ”— Details: (poonehmousavi.github.io/rg)

Convai_rg (@convai2024) 's Twitter Profile Photo

πŸ“’ Join our Conversational AI Reading Group! πŸ“… Thursday, May 1st | 11 AM - 12 PM EST πŸŽ™ Speaker: Daniel Povey from Xiaomi Corp. πŸ“– Topic: "CR-CTC: Consistency regularization on CTC for improved speech recognition" πŸ”— Details: (poonehmousavi.github.io/rg)

Convai_rg (@convai2024) 's Twitter Profile Photo

πŸ“’ Join our Conversational AI Reading Group! πŸ“… Thursday, May 8th | 11 AM - 12 PM EST πŸŽ™ Speaker: Leda Sari πŸ“– Topic: "The Voicebox Model and Its Applications" πŸ”— Details: (poonehmousavi.github.io/rg)

Convai_rg (@convai2024) 's Twitter Profile Photo

πŸ“’ Join our Conversational AI Reading Group! πŸ“… Thursday, May 15th | 11 AM - 12 PM EST πŸŽ™ Speaker: Wen-Chin Huang (Wen-Chin Huang) πŸ“– Topic: "Automatic Quality Assessment for Speech and Beyond" πŸ”— Details: (poonehmousavi.github.io/rg) , (youtube.com/@CONVAI_RG)

Wen-Chin Huang (@unilightwf) 's Twitter Profile Photo

Convai_rg Thank you for having me, and thank you all the listeners! I had a great time πŸ™Œ If you missed it, here's the recording and the slides! Recording: youtube.com/watch?v=REH034… Slides: poonehmousavi.github.io/assets/slides/…

Convai_rg (@convai2024) 's Twitter Profile Photo

πŸ“’ Join our Conversational AI Reading Group! πŸ“… Thursday, May 22nd | 11 AM - 12 PM EST πŸŽ™ Speaker: HervΓ© Bredin (HervΓ© "pyannote" Bredin) πŸ“– Topic: "Speaker diarization, a (love) loss story" πŸ”— Details: (poonehmousavi.github.io/rg)

HervΓ© "pyannote" Bredin (@hbredin) 's Twitter Profile Photo

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

... in which I'll talk about my decade-old love for speaker diarization and the loss functions used to train underlying neural networks
HervΓ© "pyannote" Bredin (@hbredin) 's Twitter Profile Photo

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

Convai_rg (@convai2024) 's Twitter Profile Photo

πŸ“’ Join our Conversational AI Reading Group! πŸ“… Thursday, May 29th | 11 AM - 12 PM EST πŸŽ™ Speaker: Yossi Adi Yossi Adi πŸ“– Topic: "On The Landscape of Spoken Language Models" πŸ”— Details: (poonehmousavi.github.io/rg)

Convai_rg (@convai2024) 's Twitter Profile Photo

πŸš€ If you missed the May 29th session on the landscape of spoken language models by Yossi Adi (Yossi Adi ), the full session is now available on our YouTube channel! πŸŽ₯ πŸ“Ί Watch here: youtu.be/2d1MU280yQk?si… πŸ“‘ Slides available here: poonehmousavi.github.io/rg.html

Convai_rg (@convai2024) 's Twitter Profile Photo

πŸ“’ Join our Conversational AI Reading Group! πŸ“… Thursday, June 5th | 11 AM - 12 PM EST πŸŽ™ Speaker: Herman Kamper (Herman Kamper) πŸ“– Topic: "Voice conversion and the geometry of self-supervised speech representations" πŸ”— Details: (poonehmousavi.github.io/rg)

Convai_rg (@convai2024) 's Twitter Profile Photo

πŸ“’ Join our Conversational AI Reading Group! πŸ“… Thursday, June 12th | 11 AM - 12 PM EST πŸŽ™ Speaker: Andros Tjandra πŸ“– Topic: "Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound" πŸ”— Details: (poonehmousavi.github.io/rg)

Pooneh Mousavi (@mousavipooneh) 's Twitter Profile Photo

πŸš€ We're excited to announce our latest work: "Discrete Audio Tokens: More Than a Survey!" It presents a comprehensive survey and benchmark of audio tokenizers across speech, music, and general audio. preprint: arxiv.org/pdf/2506.10274 website: poonehmousavi.github.io/dates-website/

Gallil Maimon (@gallilmaimon) 's Twitter Profile Photo

πŸŽ΅πŸ’¬ If you are interested in Audio Tokenisers, you should check out our new work! We empirically analysed existing tokenisers from every way - reconstruction, downstream, LMs and more. Grab yourself a β˜•/🍺 and sit down for a read!

πŸŽ΅πŸ’¬ If you are interested in Audio Tokenisers, you should check out our new work!
We empirically analysed existing tokenisers from every way - reconstruction, downstream, LMs and more.

Grab yourself a β˜•/🍺 and sit down for a read!
Convai_rg (@convai2024) 's Twitter Profile Photo

πŸ“’ Join our Conversational AI Reading Group! πŸ“… Thursday, June 19th | 11 AM - 12 PM EST πŸŽ™ Speaker: Yuki Mitsufuji (Yuki Mitsufuji) - SonyAI πŸ“– Topic: "AI for Creators: Pushing Creative Abilities to the Next Level" πŸ”— Details: (poonehmousavi.github.io/rg)

Convai_rg (@convai2024) 's Twitter Profile Photo

πŸ“’ Join our Conversational AI Reading Group! πŸ“… Thursday, June 26th | 11 AM - 12 PM EST πŸŽ™ Speaker: Dinesh Manocha (Dinesh Manocha) - University of Maryland πŸ“– Topic: "Audio Processing in the Age of Large Language Models" πŸ”— Details: (poonehmousavi.github.io/rg)

Convai_rg (@convai2024) 's Twitter Profile Photo

πŸ“’ The Conversational AI Reading Group is on summer break in July & August. We'll return in September with exciting new speakers! Catch up on past sessions here: πŸ”— Website: poonehmousavi.github.io/rg πŸ“Ί YouTube: youtube.com/@CONVAI_RG