IWSDS 2026

Overview

The 16th International Workshop on Spoken Dialogue Systems Technology (IWSDS 2026) will be held on February 26th - March 1st, 2026 in Trento, Italy. IWSDS 2026 aims to bring together researchers in speech and natural language processing who investigate spoken dialogue, advancing the science and engineering of dialogue modeling, system development, and real-world applications. 

This year’s theme “Human-Machine Dialogue in the Era of Multimodal Foundation Models (MFM)” highlights opportunities to connect our dialogue systems community with research areas in machine learning, computer vision, robotics and extended reality; and foster collaborations that extend, ground, and safely deploy new models for real-time, robust, and human-centered conversational AI systems. 

Submission Topics

We invite submissions of long papers, short papers, position papers, industry track papers, and demonstrations on a broad range of topics related to the Theoretical Foundations, Systems and Methods, and Applications of spoken and multimodal dialogue systems. Topics of interest include, but are not limited to, the following areas:

 Theoretical Foundations: 

• Multimodal and situated dialogue models

• Integration and control of modalities and context 

• Incremental and longitudinal dialogue models

• Emotion, engagement, and interaction styles 

• Ethical, trustworthy, and responsible dialogue systems

• Bias, toxicity, and harm in dialogue systems

Systems and Methods:

• Multimodal Models (foundation, small or task-specific pre-trained models) for Dialogue Systems

• Multimodal Models for grounding, personalization, safety, and explainability

• Dialogue generation and management

• Grounded and adaptive Natural Language Generation

• Domain transfer and adaptation techniques

• Evaluation methods and multimodal metrics

• Resources, corpora creation, annotation

Applications:

• Educational and healthcare applications

• Low-resource and multilingual settings

• Robotics and embodied dialogue systems

• Dialogue in Virtual and Extended Reality

• Real-world dialogue systems

Industry Track:

In addition to the regular research tracks, IWSDS 2026 will feature a dedicated Industry Track, aimed at companies, startups, and applied research groups, in order to reinforce knowledge sharing across academia and industry. Submissions to this track should focus on real-world applications, systems, challenges, and lessons learned in spoken and multimodal dialogue systems. Submissions in the Industry Track should have the following characteristics:

1. The submission should describe deployed systems, prototypes, user studies, or integration efforts;

2. The submission does not need to share data or code, but clear data/system descriptions and evaluation results are expected. 

Submissions in this track are reviewed according to practical impact, innovation, and relevance, rather than purely on novelty. We particularly encourage submissions from companies that wish to showcase how dialogue technology is applied in real products, services, or large-scale deployments.

Paper Submission Details

Submission types:

• Long papers (up to 8 pages + references)

• Short papers (up to 4 pages + references)

• Position papers and Demo papers (up to 4 pages + references)

• Industry Track papers. (up to 4 pages + references)

All submissions will undergo double-blind peer review. Accepted papers will be included in the workshop proceedings, published on the ACL Anthology. Authors are asked to use the following templates for paper submissions. 

We look forward to your contributions and to welcoming you to IWSDS26 for an engaging and forward-looking workshop.

Important Dates

Paper Submission  (PDF) Deadline: October 12th, 2025

Paper Update (PDF) Deadline: October 18th, 2025

Paper Acceptance Notification: December 10th, 2025

Camera Ready Papers Due: January 12th, 2026

Early Registration: December 10th, 2025 - January 12th, 2026

Regular Registration: From January 13th, 2026

Workshop: February 26th – March 1st 2026

All deadlines are 11.59 pm UTC -12h (anywhere on earth).