Interspeech 2026 Tutorial

On the Landscape of Spoken Language Models

Sunday, 27 September 2026 · Morning session International Convention Centre Sydney
TMLR survey paper Slides (PDF)

Contact: Kai-Wei Chang <kwchang at mit.edu>

Program

  1. 01
    Introduction
    Kai-Wei Chang
  2. 02
    Speech representation
    Chung-Ming Chien
  3. 03
    Typical training
    Shinji Watanabe
  4. 04
    Advanced training
    Kai-Wei Chang
  5. 05
    Hands-on session
    Ke-Han Lu
    Code on GitHub →
  6. 06
    Full-duplex spoken language models
    Siddhant Arora
  7. 07
    Evaluation
    Hung-yi Lee
  8. 08
    Emerging topics
    Chih-Kai Yang
  9. 09
    Conclusion
    Karen Livescu

Speakers

Kai-Wei Chang
Kai-Wei Chang
Chung-Ming Chien
Chung-Ming Chien
Shinji Watanabe
Shinji Watanabe
Ke-Han Lu
Ke-Han Lu
Chih-Kai Yang
Chih-Kai Yang
Siddhant Arora
Siddhant Arora
Hung-yi Lee
Hung-yi Lee
Karen Livescu
Karen Livescu

Survey paper

The tutorial is based on our survey.

First page of the survey paper

On The Landscape of Spoken Language Models: A Comprehensive Survey

Siddhant Arora*, Kai-Wei Chang*, Chung-Ming Chien*, Yifan Peng*, Haibin Wu*, Yossi Adi†, Emmanuel Dupoux†, Hung-yi Lee†, Karen Livescu†, Shinji Watanabe†

* Co-first authors  ·  † Co-last authors  (alphabetical within each group)

Transactions on Machine Learning Research (TMLR), 2025

arXiv