Participate
Table of Contents
- Location
- Registration
- Program
- Tentative Agenda
- Keynote Speakers
- Panel Discussion
- Call for Papers
- Submissions
- Contact
Location
The full-day 2026 LRAC Workshop will take place in Barcelona, Spain on Monday, May 4, 2026.
Venue: International Barcelona Convention Center (CCIB) (ICASSP 2026 Venue).
Registration
-
Registration for the 2026 LRAC Workshop is part of the ICASSP 2026 Registraion process.
-
If you are attending only the workshop: In Section 4 - Registration Selection, select Workshop Full-Day Only (note: main conference registration is not included).
-
If you are attending the main conference: In Section 4 - Registration Selection, select one of the Conference Registration options. Then, in Section 5 - Optional Events, add the LRAC Workshop.
-
If you have already registed for the main conference: You can add the LRAC Workshop to your registration by logging into the ICASSP 2026 Registration page and selecting LRAC Workshop in Section 5 - Optional Events.
-
-
Capacity is strictly limited and available on a first-come, first-served basis. Please consider registering for the workshop as soon as possible.
Program
A PDF version of the Workshop Program: coming soon…
Tentative Agenda
Morning Block
| Time | Session | Duration | Agenda |
|---|---|---|---|
| 08:30 – 09:00 | Poster Setup | 30 min | Time allocated for poster setup to help ease the flow of the morning block |
| 09:00 – 09:10 | Opening Talk | 10 min | Brief talk about the workshop by the organizers |
| 09:10 – 09:55 | First Keynote | 45 min | Keynote by Jean-Marc Valin (Google) Title: From Paper to Production: the Engineering and Standardization Challenges of Neural Speech Coding |
| 09:55 – 10:15 | Challenge Overview | 20 min | Challenge overview talk by the challenge organizers |
| 10:15 – 10:30 | Lightning Talks | 15 min | Lightning talks: select papers |
| 10:35 – 11:00 | Coffee Break | 25 min | Coffee break provided by ICASSP organizers. |
| 11:00 – 12:30 | Poster Session | 90 min | Poster session. Authors free to roam after 60 min. |
Lunch Break
| Time | Session | Duration | Agenda |
|---|---|---|---|
| 12:30 – 14:30 | Lunch Break | 120 min | Self-arranged lunch break. Lunch is not provided by the workshop. |
Afternoon Block
| Time | Session | Duration | Agenda |
|---|---|---|---|
| 14:30 – 15:15 | Second Keynote | 45 min | Keynote by Nicola Pia (Fraunhofer IIS) Title: Design Choices and Effective Evaluation of Modern Speech and Audio Codecs Based on Neural Networks |
| 15:15 – 16:00 | Oral Presentations | 45 min | Oral presentations: select papers. |
| 16:05 – 16:20 | Coffee Break | 15 min | Coffee break provided by ICASSP organizers. |
| 16:20 – 17:05 | Third Keynote | 45 min | Keynote by Cullen Jennings (Cisco Systems) Title: More Bandwidth, More Problems: Audio Codecs in the Machine Learning Era |
| 17:05 – 18:05 | Panel Discussion | 60 min | Panel Discussion Host: Minje Kim Panelists: Yossi Adi, Nicola Pia, Jean-Marc Valin, and Cullen Jennings Topic: Are Neural Codecs Ready for Low-Resource Reality? Potentials and Pitfalls in the AI Era. |
Evening Event
| Time | Session | Duration | Agenda |
|---|---|---|---|
| 19:00 – 21:30 | Conference Reception | 150 min | ICASSP’s Welcome Reception |
Keynote Speakers
Jean-Marc Valin (Senior Staff Research Scientist, Google)
Keynote
From Paper to Production: the Engineering and Standardization Challenges of Neural Speech Coding
Bio
Jean-Marc Valin is a Senior Staff Research Scientist at Google and a long-time contributor to the Xiph.Org Foundation. He received his B.A.Sc., M.S., and Ph.D. in Electrical Engineering from the University of Sherbrooke, Canada. He is a lead architect of the Opus and Speex audio codecs and also contributed to the AV1 video codec. His research focuses on speech and audio coding, neural vocoders (LPCNet, FARGAN), and deep-learning-based speech enhancement. He was previously at Amazon Web Services and Mozilla.
Nicola Pia (Senior Scientist, Fraunhofer IIS)
Keynote
Design Choices and Effective Evaluation of Modern Speech and Audio Codecs Based on Neural Networks
Bio
Nicola Pia is a Senior Scientist at Fraunhofer IIS in Erlangen, Germany. He studied Mathematics at the Università di Cagliari and spent the final year of his master’s degree at the Université de Strasbourg. He later pursued a PhD in Mathematics, conducting his research between the Università di Cagliari and the Ludwig-Maximilians-Universität (LMU) in Munich. After receiving his doctorate in 2019, he won a DAAD grant and completed a brief post-doctoral fellowship at LMU.
Since joining Fraunhofer (2019), his work has focused on speech and audio coding, with a particular emphasis on communication with mobile devices. He authored many papers and is the inventor of several patents on this subject. Moreover, he teaches a course on deep generative models for signal processing at the Friedrich-Alexander-Universität Erlangen-Nürnberg.
Since joining Fraunhofer (2019), his work has focused on speech and audio coding, with a particular emphasis on communication with mobile devices. He authored many papers and is the inventor of several patents on this subject. Moreover, he teaches a course on deep generative models for signal processing at the Friedrich-Alexander-Universität Erlangen-Nürnberg.
Cullen Jennings (Fellow and CTO for Collaboration AI, Cisco Systems)
Keynote
More Bandwidth, More Problems: Audio Codecs in the Machine Learning Era
Bio
Cullen Jennings is a Fellow and CTO for Audio/Video Collaboration and AI at Cisco, where he drives the vision and strategy for collaboration technology, including AI research and development. Since the '90s, he has worked on VoIP systems that now host billions of minutes of audioconferencing daily, driven internet voice communications standards, and spearheaded the development of WebRTC. His industry leadership has shaped numerous open-source and standards organizations, and he holds 100+ patents.
Cullen joined Cisco in 2000 through the acquisition of Vovida Networks, where he was VP of Engineering. He is also co-founder of Jasomi Networks and Point Grey Research, and holds a Ph.D. in computer science from the University of British Columbia.
Cullen joined Cisco in 2000 through the acquisition of Vovida Networks, where he was VP of Engineering. He is also co-founder of Jasomi Networks and Point Grey Research, and holds a Ph.D. in computer science from the University of British Columbia.
Panel Discussion
Topic: Are Neural Codecs Ready for Low-Resource Reality? Potentials and Pitfalls in the AI Era.
Host: Minje Kim (Associate Professor, UIUC)
Minje Kim is an Associate Professor at the UIUC and an Amazon Scholar. He chairs the IEEE AASP TC and has organized various workshops, including IEEE WASPAA 2023 and HSCMA 2024. He has over 20 years of experience in machine learning and audio signal processing, with a focus on neural speech/audio coding and model compression.
Panelist: Yossi Adi (Assistant Professor, Hebrew University of Jerusalem)
Yossi Adi is an Assistant Professor at the School of Computer Science at the Hebrew University of Jerusalem. Yossi has been a member of several technical committees, including IEEE-MLSP, MLSLP. He co-organized two special sessions and gave a tutorial talk on spoken language models at Interspeech-2024.
Panelist: Nicola Pia (Senior Scientist, Fraunhofer IIS)
Nicola Pia is a Senior Scientist at the Fraunhofer IIS in Erlangen, Germany. He received his PhD in Mathematics from the University of Cagliari in 2019. Since joining Fraunhofer (2019), his work has focused on speech and audio coding, with a particular emphasis on communication with mobile devices.
Panelist: Jean-Marc Valin (Senior Staff Research Scientist, Google)
Jean-Marc Valin is a Research Scientist at Google and a long-time contributor to the Xiph.Org Foundation. He received his Ph.D. from the University of Sherbrooke. He is a lead architect of the Opus and Speex audio codecs. His research focuses on speech and audio coding, and speech enhancement.
Panelist: Cullen Jennings (Fellow and CTO, Cisco Systems)
Cullen Jennings is a Cisco Fellow and CTO for Audio/Video Collaboration and AI. He has worked on VoIP systems since the ‘90s, building platforms hosting billions of audioconferencing minutes a day. He drives standards for major internet voice communications and leads Cisco's collaboration technology vision, strategy, and AI research development. Cullen holds a Ph.D. in computer science from the University of British Columbia.
Call for Papers
The PDF version of the Call for Papers: LRAC-Workshop-Call-for-Papers.pdf
Submissions
Information regarding workshop’s paper submissions is summarized in: https://lrac.short.gy/workshop-tracks
Contact
In case you have questions, you can reach us via email: lrac-workshop@cisco.com.