📢 This week at our Conversational AI Reading Group, We’re happy to welcome : 📖 The Grand Design Challenge of Music GenAI. 📅 Thursday, May 14 | 11:00 AM – 12:00 PM EST 🎙 Speaker: Nicholas J. Bryan - Adobe Research

📢 This week at our Conversational AI Reading Group, We’re happy to welcome : 📖 Large Audio-Language Models: Algorithms and Applications. 📅 Thursday, April 30 | 11:00 AM – 12:00 PM EST 🎙 Speaker: Wenwu Wang - University of Surrey

📢 This week at our Conversational AI Reading Group, We’re happy to welcome : 📖 Improving spoken language identification for non-native speech. 📅 Thursday, April 23 | 11:00 AM – 12:00 PM EST 🎙 Speaker: Tanel Alumäe ( @tanelalumae.bsky.social ) - Tallinn University of Technology

📢 This week at our Conversational AI Reading Group, We’re happy to welcome : 📖 Toward Trustworthy Voice Agents: Speech-Native Evaluation, Safety, and Security. 📅 Thursday, April 16 | 11:00 AM – 12:00 PM EST 🎙 Speaker: Amir Ivry - Technion, incoming CMU

📢 This week at our Conversational AI Reading Group, We’re happy to welcome : 📖 Faithful and Grounded Audio Language Models.. 📅 Thursday, April 9 | 11:00 AM – 12:00 PM EST 🎙 Speaker: Cem Subakan - Mila 🔗 Details: poonehmousavi.github.io/rg.html @mila-quebec.bsky.social

📢 This week at our Conversational AI Reading Group, We’re happy to welcome : 📖 Voice-Based Psychiatric Assessment in the Real World and the Case for Production-Aligned Speech Frontends. 📅 Thursday, April 2 | 11:00 AM – 12:00 PM EST 🎙 Speaker: George Fairs & Stefano Goria - thymia

📢 This week at our Conversational AI Reading Group, We’re happy to welcome : 🎙 Speaker: Jonathan Le Roux ( @jonathanleroux.bsky.social .bsky.social ) - MERL 📖 Prompt-Conditioned Unified Audio Modeling: From Source Separation to Source-Aware Codecs. 📅 Thursday, March 26 | 11:00 AM – 12:00 PM EST

📢 This week at our Conversational AI Reading Group, We’re happy to welcome : 🎙 Speaker: Andros Tjandra & Bowen Shi - FAIR (Meta AI) 📖 SAM Audio: Segment Anything in Audio. 📅 Thursday, March 19 | 11:00 AM – 12:00 PM EST

📢 This week at our Conv AI Reading Group, We’re happy to welcome : 🎙 Speaker: Ricard Marxer ( @ricard.bsky.social) - Université de Toulon, ILLS, CNRS 📖 Advancing the Linguistic Capabilities of Speech Language Models. 📅 Thursday, March 12 | 11:00 AM – 12:00 PM EST

📢 This week at our Conversational AI Reading Group, We’re happy to welcome : 🎙 Speaker: Yiwen Shao - Tencent AI Lab 📖 Auden: From audio encoders to Large Audio Language Model. 📅 Thursday, March 5 | 11:00 AM – 12:00 PM EST 🔗 Details: poonehmousavi.github.io/rg.html

📢 This week at our Conversational AI Reading Group: We’re happy to welcome : 🎙 peaker: Samuele Cornell @popcornell.bsky.social - Carnegie Mellon University 📖 Conversational Speech Processing: Challenges & Opportunities 📅 Thursday, Feb 26 | 11:00 AM – 12:00 PM EST

📢 This week at our Conversational AI Reading Group, We’re happy to welcome : 🎙 Speaker: Tiago H. Falk - INRS 📖 Amplitude Modulation Spectral Analysis: From Conventional Audio Feature Engineering to Speech Foundation Models 📅 Thursday, Feb 19 | 11:00 AM – 12:00 PM EST

📢 This week's Talk: 📖 Towards Accountable Conversational Agents for Task Completion 📅 Thursday, Feb 12 | 11:00 AM – 12:00 PM EST 🎙 Speaker: Dilek Hakkani-Tür - UIUC @dilekh.bsky.social ▶️ YouTube channel: youtube.com/@CONVAI_RG 🔗 Details: poonehmousavi.github.io/rg

ConvAI_RG

Conversational AI Reading Group

youtube.com

📢 This week’s talk: 📖 Model-based audio deep learning with application to source separation and dereverberation 📅 Thursday, Feb 5 | 11:00 AM – 12:00 PM EST 🎙 Speaker: Gaël Richard —Télécom Paris), ▶️ YouTube channel: www.youtube.com/@CONVAI_RG 🔗 Details: poonehmousavi.github.io/rg.html

ConvAI_RG

Conversational AI Reading Group

youtube.com

🎉 ConvAI Reading Group is back for 2026! This week we welcome Daniel P. W. Ellis (Google DeepMind) presenting his ICML paper: 🎧 Recomposer: Event-roll-guided Audio Editing 📅 Thu, Jan 29 | 11 AM EST 🔗 poonehmousavi.github.io/rg.html ▶️ youtube.com/@CONVAI_RG

📢 Join the final Conversational AI Reading Group meeting of 2025! 📅 Thursday, Dec 18th | 11 AM - 12 PM EST 🎙 Speaker: Daniel D'souza - Cohere Labs 📖 Topic: "Data as Leverage: Improving Foundation Models Beyond Scaling." 🔗 Details: poonehmousavi.github.io/rg.html @cohereforai.bsky.social

📢 Join our Conversational AI Reading Group! 📅 Thursday, Dec 11th | 11 AM - 12 PM EST 🎙 Speaker: Tatiana Likhomanenko - Apple 📖 Topic: "Low-latency Conversational Agent." 🔗 Details: poonehmousavi.github.io/rg.html

📢This week, our Conversational AI Reading Group is excited to have Juan Rafael Orozco-Arroyave from Universidad de Antioquia. 📅 Thursday, Nov 27th | 11 AM - 12 PM EST 📖 Topic: "Multimodal analysis of Parkinson’s disease symptoms." 🔗 Details: (poonehmousavi.github.io/rg)

📢 Join our Conversational AI Reading Group. ⚠️Please note this talk starts at 10:00 AM (EST) as an exception. 📅 Thursday, Nov 20th | 10 AM - 11AM EST 🎙 Speaker: Marc Delcroix - NTT Communication Science Laboratories 📖 Topic: "Neural Target Speech and Sound Extraction" 🔗 Details: (lnkd.in/eWruCDV6)

📢 Join our Conversational AI Reading Group! 📅 Thursday, Nov 13th | 11 AM - 12 PM EST 🎙 Speaker: Simone Scardapane (@sscardapane.bsky.social ) - Sapienza University of Rome 📖 Topic: "Efficient and resource-constrained dynamic neural networks" 🔗 Details: (poonehmousavi.github.io/rg)

📢 Join our Conversational AI Reading Group! 📅 Thursday, Nov 6th | 11 AM - 12 PM EST 🎙 Speaker: Emmanouil Benetos ( @emmanouilb.bsky.social ) - Queen Mary University of London 📖 Topic: "Machine learning paradigms for music and audio understanding" 🔗 Details: (poonehmousavi.github.io/rg)

📢 Join our Conversational AI Reading Group to know more about Google Gemini 2.5, a natively multimodal audio model developed over the past year. 📅 Thursday, Oct 30th | 11 AM - 12 PM EST 🎙 Speaker: Michael Han - Google DeepMind 🔗 Details: (poonehmousavi.github.io/rg)

📢 Join our Conversational AI Reading Group! 📅 Thursday, Oct 23rd | 11 AM - 12 PM EST 🎙 Speaker: Joan Serrà ( @serrjoa.bsky.social ) - Sony AI 📖 Topic: "Supervised contrastive learning from weakly-labeled audio segments for musical version matching" 🔗 Details: (poonehmousavi.github.io/rg)

📢This week, our Conversational AI Reading Group is excited to have Jinyu Li from Microsoft. Please note: This week’s session will start one hour later than usual, at 12:00 PM instead of 11:00 AM. 📅 Thursday, Oct 16th | 12:00 - 13:00 EST 📖 Topic: "The development of spoken LM"

📢 Schedule Update! The Oct 9th session will start 15 minutes earlier than usual at 10:45 AM. Please make sure to mark this change in your calendar so you don’t miss it!

@convai-rg.bsky.social · 10mo ago

📢This week, our Conversational AI Reading Group is excited to have Fabio Antonacci from Politecnico di Milano. 📅 Thursday, Oct 9th | 11 AM - 12 PM EST 🎙 Speaker: Fabio Antonacci - Politecnico di Milano 📖 Topic: "AI-based Spatial Audio" 🔗 Details: (lnkd.in/eWruCDV6)

📢This week, our Conversational AI Reading Group is excited to have Fabio Antonacci from Politecnico di Milano. 📅 Thursday, Oct 9th | 11 AM - 12 PM EST 🎙 Speaker: Fabio Antonacci - Politecnico di Milano 📖 Topic: "AI-based Spatial Audio" 🔗 Details: (lnkd.in/eWruCDV6)

If you missed Yoshua Bengio 's session presenting “A safety case for the Scientist AI”, you can now find the recording on our YouTube channel and the slides on our website: YouTube: youtu.be/bzORaP6cAGI Website: poonehmousavi.github.io/rg.html

A safety case for the Scientist AI - Yoshua Bengio

YouTube video by ConvAI_RG

youtu.be

@convai-rg.bsky.social · 11mo ago

This Thursday Oct 2nd , our Conversational AI RG is honored to host @yoshuabengio.bsky.social , one of the world’s leading pioneers in AI. He will present: “A Safety Case for the Scientist AI.” Don’t miss this unique opportunity to join us online ! 🔗 Details: poonehmousavi.github.io/rg.html

This Thursday Oct 2nd , our Conversational AI RG is honored to host @yoshuabengio.bsky.social , one of the world’s leading pioneers in AI. He will present: “A Safety Case for the Scientist AI.” Don’t miss this unique opportunity to join us online ! 🔗 Details: poonehmousavi.github.io/rg.html

📢 Join our Conversational AI Reading Group! 📅 Thursday, Sep 25th | 11 AM - 12 PM EST 🎙 Speaker: Themos Stafylakis 📖 Topic: "Advances in Speaker Recognition: Pruning, Deepfake Detection, and Learning without Temporal Labels" 🔗 Details: (poonehmousavi.github.io/rg)

📢 Our Conversational AI Reading Group is back! Join the first Fall 2025 session! 🤖 📅 Thursday, Sept 18 | 11 AM–12 PM EST 🎙 Speaker: Pooneh Mousavi (Mila) @MousaviPooneh 📖 Topic: “Discrete Audio Tokens: More Than a Survey!” 🌐 Details: poonehmousavi.github.io/rg