The 2nd Workshop of Multimodal, Multilingual and Multitask Modeling Technologies for Oriental Languages (M3Oriental)

Abstract 

This M3Oriental workshop addresses the challenges in low-resourced language problems in speech and language processing. The workshop focuses on integrating multimodal, multilingual, and multitask modeling technologies using large-scale pretraining models. The goal is to explore their potential in multimodal tasks and cross-lingual communication, which are key features of next-generation artificial intelligence. The workshop covers multiple tasks (such as machine translation (MT), speech translation (ST), speech recognition (ASR), speech synthesis (TTS), voice conversion (VC), and speech emotion recognition (SER)). 

Scope of the Workshop

We welcome any original, interdisciplinary research related to the M3Oriental. This year, the workshop will be focused on the following topics:

• Audio, Speech and Language Processing; 

• Datasets, Benchmark Systems and Models;

Submission: Papers on M3Oriental can be submitted to the workshop through the ACM Multimedia Asia 2024 author console of the paper management system (CMT): Paper Submission link. 

Select Track 8: M3Oriental: Workshop of Multimodal, Multilingual and Multitask Modeling Technologies for Oriental Languages (shown in above picture).

We invite submissions of original technical papers related to the M3Oriental (topics of this workshop), including but not limited to:

• Audio, Speech and Language Processing; 

• Datasets, Benchmark Systems, Models and Shared Tasks;

Paper format: Submitted papers should be within the scope of the workshop. The submitted workshop papers follow the ACM Multimedia Asia-2024 paper style, format, and 2 to 6 pages (Paper Submission Guidelines), but are single-blind.

In-person or online: The Satellite Workshops will be held with in-person (online just in case) attendance. Accordingly, each accepted workshop paper must be presented in-person (online just for personal health, VISA, or national restrictions) by one of the authors. 

Registration: The main conference will provide the registration with the official entry of the workshop paper. One main conference paper can cover one workshop paper. Note that if the authors of workshop papers would like to attend the main conference, it requires the main conference registration.

Publication: Upon acceptance, paper authors will have the opportunity to present their paper at our workshop, and the workshop paper will be included in the workshop proceedings belonging to the ACM MMAsia2024.

Important dates

• Workshop Paper Submission Deadline: Sept.27 

• Workshop Paper Acceptance Notification: Oct. 14

• Workshop Camera Ready Paper Deadline: Oct. 25

Accepted resource/toolkit/benchmark papers

TBD

We also have a speech recognition challenge in preparation. 

TBD

Paper presentations are posters. Please see the 3-minute videos and PDF posters from the Gather town.

Communication is possible throughout the entire meeting.

ID Speaker (Affiliation), et al., Title

Following is the keynote speech scheduled at the Zoom meeting and on-site:

The Zoom meeting link is: ***

The password of all Zoom meeting rooms is: ***

Speech

Ruili Wang, Massey Univ., New Zealand (ruili.wang-a-t-massey.ac.nz )

Sheng Li, NICT, Kyoto, Japan, Researcher (sheng.li-a-t-nict.go.jp)

NLP

Chenhui Chu, Kyoto Univ., Kyoto, Japan, Associate Professor (chu-a-t-i.kyoto-u.ac.jp)

Dr. Jiyi Li,  Univ. Yamanashi, Japan,  Associate Professor  (jyli-a-t-yamanashi.ac.jp)

Raj Dabre, NICT., Kyoto, Japan, Researcher (raj.dabre-a-t-nict.go.jp)

Multimodal

Xianchao Wu, NVIDIA, Tokyo, Japan, Senior Solution Architect (xianchaow-a-t-nvidia.com)

Bei Liu, MSRA, Beijing, China, Senior Researcher (bei.liu-a-t-microsoft.com)

Zuchao Li, Wuhan Univ., China, Associate Professor (zcli-charlie-a-t-whu.edu.cn)

Security

Yang Cao, TokyoTech., Tokyo, Japan, Associate Professor (cao-a-t-c.titech.ac.jp )

Zhao Ren, Univ. Bremen, Germany, Researcher (zren-a-t-uni-bremen.de)