Can we understand speech across languages without transcribing it first? π
π Yannick EstΓ¨ve (Avignon UniversitΓ©): "Learning Sentence-Level Speech Representations"
π
Thu, Oct 22 Β· 11amβ12pm ET Β· online, open to all
Details & Zoom: poonehmousavi.github.io/rg.hβ¦
What if you could design a soundscape by describing it, imitating it with your voice, or showing a video?
π Oriol Nieto (Adobe Research): "Sound Design AI"
π
Thu, Oct 15 Β· 11amβ12pm ET Β·
Details & Zoom: poonehmousavi.github.io/rg.hβ¦
@urinieto #ConvAIRG #AudioAI
Convai_rg retweeted
π£ Our ICASSP 2027 workshop welcomes work on explainability, robustness, and controllability in speech and audio broadly. No need to focus on audio language models (ALMs) only.
Submissions are open!
ποΈ Deadline: Nov 11, 2026 (AoE)
cmsworkshops.com/ICASSP2027/β¦
π’ The Conversational AI Reading Group is back for Fall 2026!
π First talk: Sreyan Ghosh (Google DeepMind), "Towards Fully Open General Audio Intelligence"
π
Thu, Oct 8 Β· 11amβ12pm ET Β· online, open to all
Schedule & Zoom: poonehmousavi.github.io/rg.hβ¦
@SreyanG #ConvAIRG
Convai_rg retweeted
π’ I'm happy to share that our workshop on Explainability, Robustness, and Controllability of Language Modeling for Speech and Audio was accepted at @ieeeICASSP !
If you have ongoing relevant to these topics, consider submitting your work.
π’ This week at our Conversational AI Reading Group, Weβre happy to welcome :
π The Grand Design Challenge of Music GenAI.
π
Thursday, May 14 | 11:00 AM β 12:00 PM EST
π Speaker: Nicholas J. Bryan - Adobe Research
π’ This week at our Conversational AI Reading Group, Weβre happy to welcome :
π Large Audio-Language Models: Algorithms and Applications.
π
Thursday, April 30 | 11:00 AM β 12:00 PM EST
π Speaker: Wenwu Wang - University of Surrey
π’ This week at our Conversational AI Reading Group, Weβre happy to welcome :
π Improving spoken language identification for non-native speech.
π
Thursday, April 23 | 11:00 AM β 12:00 PM EST
π Speaker: Tanel AlumΓ€e (@TanelAlumae) - Tallinn University of Technology
π’ π’ This week at our Conversational AI Reading Group, Weβre happy to welcome :
π Toward Trustworthy Voice Agents: Speech-Native Evaluation, Safety, and Security.
π
Thursday, April 16 | 11:00 AM β 12:00 PM EST
π Speaker: Amir Ivry - Technion, incoming CMU
π’ This week at our Conversational AI Reading Group, Weβre happy to welcome :
π Faithful and Grounded Audio Language Models.
π
Thursday, April 9 | 11:00 AM β 12:00 PM EST
π Speaker: Cem Subakan(@CemSubakan) - Mila
@Mila_Quebec
π’ This week at our Conversational AI Reading Group, Weβre happy to welcome :
π Voice-Based Psychiatric Assessment in the Real World and the Case for Production-Aligned Speech Frontends.
π
Thursday, Apr 2 | 11:00 AM β 12:00 PM EST
π George Fairs & Stefano Goria - thymia
π’ This week at our Conversational AI Reading Group, Weβre happy to welcome :
π Speaker: Jonathan Le Roux(@JonathanLeRoux) - MERL
π Prompt-Conditioned Unified Audio Modeling: From Source Separation to Source-Aware Codecs.
π
Thursday, March 26 | 11:00 AM β 12:00 PM EST
π’ This week at our Conversational AI Reading Group, Weβre happy to welcome :
π Speaker: Andros Tjandra & Bowen Shi - FAIR (Meta AI)
π SAM Audio: Segment Anything in Audio.
π
Thursday, March 19 | 11:00 AM β 12:00 PM EST
π’ This week at our Conversational AI Reading Group, Weβre happy to welcome :
π Speaker: Ricard Marxer( @ricardmp) - UniversitΓ© de Toulon, ILLS, CNRS
π Advancing the Linguistic Capabilities of Speech Language Models.
π
Thursday, March 12 | 11:00 AM β 12:00 PM EST
π’ This week at our Conversational AI Reading Group, Weβre happy to welcome :
π Speaker: Yiwen Shao - Tencent AI Lab
π Auden: From audio encoders to Large Audio Language Model.
π
Thursday, March 5 | 11:00 AM β 12:00 PM EST
π Details: poonehmousavi.github.io/rg.hβ¦
π’ This week at our Conversational AI Reading Group:
Weβre happy to welcome :
π Speaker: Samuele Cornell @SamueleCornell - Carnegie Mellon University
π Conversational Speech Processing: Challenges & Opportunities
π
Thursday, Feb 26 | 11:00 AM β 12:00 PM EST
π’ This week at our Conversational AI Reading Group:
Weβre happy to welcome :
π Speaker: Tiago H. Falk - INRS
π Amplitude Modulation Spectral Analysis: From Conventional Audio Feature Engineering to Speech Foundation Models
π
Thursday, Feb 19 | 11:00 AM β 12:00 PM EST
π’ This week's Talk:
π Towards Accountable Conversational Agents for Task Completion
π
Thursday, Feb 12 | 11:00 AM β 12:00 PM EST
π Speaker: Dilek Hakkani-TΓΌr - UIUC @dilekhakkanitur
βΆοΈ YouTube channel: youtube.com/@CONVAI_RG
π Details: poonehmousavi.github.io/rg
π’ This weekβs talk:
π Model-based audio deep learning with application to source separation and dereverberation
π
Thursday, Feb 5 | 11:00 AM β 12:00 PM EST
π Speaker: GaΓ«l Richard βTΓ©lΓ©com Paris)
βΆοΈ YouTube channel: youtube.com/@CONVAI_RG
π Details: poonehmousavi.github.io/rg.hβ¦



