Agenda of the 2nd MLC-SLM Workshop Announced for INTERSPEECH 2026

The 2nd Multilingual Conversational Speech Language Model Challenge 2026 (2nd MLC-SLM Challenge 2026) is over after several months of competition. Research teams from various countries and regions took part in the Challenge, creating models for multilingual conversational speech.

Following the first edition, this year's Challenge further widened its coverage of languages and accents by including Tagalog, Urdu, and Turkish, as well as regional accents such as Canadian French, Mexican Spanish, and Brazilian Portuguese. The Challenge consisted of two tasks related to multilingual conversational speech logging and recognition and multilingual conversational speech understanding.

The 2nd MLC-SLM Workshop will take place on October 2 in conjunction with INTERSPEECH 2026. The Workshop agenda and list of Keynote speakers have now been finalized.

The Workshop will feature five Keynote talks, the Challenge Summary & Awards Ceremony, two Oral Sessions, and a Poster Session. The final results of the 2nd MLC-SLM Challenge 2026 will be announced at the Workshop, followed by presentations from the winning teams on their systems, technical solutions, and research results.

About the 2nd MLC-SLM Workshop

Date: October 2, 2026

Venue: ICC Sydney, C2.2 & C2.3

Conference: INTERSPEECH 2026

The Workshop will gather researchers and industry professionals, as well as teams participating in the Challenge, working on multilingual conversational speech technologies. Participants will have the chance to present their work and exchange ideas through Keynote talks, Oral Sessions, and a Poster Session.

Full Workshop Agenda

Five Keynote Speakers

Five researchers and experts from the speech and AI community will give Keynote talks at the 2nd MLC-SLM Workshop.

Yonghong Yan

Yonghong Yan is a Chief Scientist at the Institute of Acoustics, Chinese Academy of Sciences. He has dedicated decades to speech signal processing and recognition. Prior to his current position, he served as Director of Intel China Research Center. He was the first researcher in the speech field to receive China's National Science Fund for Distinguished Young Scholars. In addition, he has authored over 300 papers.

Jinyu Li

Jinyu Li has worked at Microsoft since 2008. He is currently a Partner Applied Science Manager, heading research in speech, translation, and language technologies. He is an IEEE Fellow and ISCA Fellow. Among the many honors he has received are the IEEE Signal Processing Society Best Paper Award and the APSIPA Industrial Distinguished Leader Award.

Kai Yu

Kai Yu is a Distinguished Professor at the School of Computer Science of Shanghai Jiao Tong University and Director of the Institute of Machine Intelligence. In addition, he is Co-founder and Chief Scientist of AISpeech. An IEEE Fellow and ISCA Fellow, his research interests cover speech and language processing and conversational systems. He has over 300 peer-reviewed publications.

Hung-yi Lee

Hung-yi Lee is a Professor in the Department of Electrical Engineering at National Taiwan University, with a joint appointment in the Department of Computer Science and Information Engineering. His research focuses on reducing the dependence of speech and natural language processing systems on labeled data. The topics of his work include speech recognition, voice conversion, generative summarization, and question answering.

Shinnosuke Takamichi

Shinnosuke Takamichi is an Associate Professor at Keio University. He obtained his Ph.D. from the Nara Institute of Science and Technology in 2016. He has received over 20 paper and research achievement awards, including the IEEE Signal Processing Society Young Author Best Paper Award and the MEXT Young Scientists' Prize.

Keynote titles and more information about the speakers will be announced soon. Stay tuned and follow the Nexdata LinkedIn page for the latest updates on the 2nd MLC-SLM Workshop.

Challenge Results and Presentations from the Five Winning Teams

One of the main sessions of the Workshop will be the Summary & Awards Ceremony of the 2nd MLC-SLM Challenge 2026, which will take place at 11:00 AM.

The session will provide a summary of the Challenge, followed by the official announcement of the final results and winning teams. After the ceremony, five winning teams will present their work during the morning and afternoon Oral Sessions, introducing their systems, technical solutions, and research results.

Oral Session

The MOSS Systems for the MLC-SLM Challenge 2026

Transsion’s Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge

HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR

A Data-Centric LoRA Recipe for Multilingual Conversational Speech Recognition

SEAR: Segment-Evidence-Aware Routing for Weak-to-Strong Multilingual Speech MCQ

The Workshop will end with a Poster Session, where participants will be able to present their work and discuss their research with other attendees.

Register for the 2nd MLC-SLM Workshop

There are two ways to register for the Workshop. The participation fee is AUD 80.

Option 1: Registration through INTERSPEECH 2026

Participants can select the 2nd MLC-SLM Workshop when registering for INTERSPEECH 2026.

INTERSPEECH 2026 Registration

Option 2: Registration via the Workshop Registration Form

Participants can fill out the Workshop registration form in advance and pay the AUD 80 registration fee on site.

Workshop Registration Form

Hope to see you on October 2 in Sydney at INTERSPEECH 2026.