Introduction

Modern transportation is no longer powered by fuel or electricity alone. It is powered by information as well. The transportation system has come to an era where the abundant information and the advanced machine learning, data mining, and decision-making algorithms can join forces to solve the issues we face in transportation and make it more intelligent and efficient. We propose a workshop at Interspeech for the professionals, researchers, and practitioners who are interested in speech interaction related research within the mobility system.

This workshop will include a special session focused on “target speaker aware speech synthesis and voice conversion”. During the workshop, DiDi will release a new large scale open dataset to the academic community for research purposes.

Location

Due to COVID-19 pandemic, SLIMTS 2020 is now planned as a fully virtual event. Details of the virtual event platform will be announced before the workshop date.

Call for papers

In this workshop, we invite professionals, researchers and technologists of all relevant fields to present the state-of-the-art development and applications as well as share their visions about the future of speech interaction technology within mobility. The topics of interests include, but not limited to, the following aspects:

- Acoustic Signal Processing for Mobile Transportation System
- Speech Recognition
- Speech Synthesis
- Spoken Language Understanding and Dialog for Mobile Transportation System
- Speaker Recognition

We encourage extended abstracts or 4-page full papers. All submissions must be in English and in the PDF format. Full paper submissions should not exceed the appropriate length requirements in the current INTERSPEECH two-column conference format.

Full papers (4 pages with an optional 5th page only for references) must be original and should not have been published previously or be under consideration for publication while being evaluated for this workshop.

We will follow a single-blind process and submissions will be evaluated by the program committee based on the quality of the work and the relevance to the workshop themes. All papers are to be submitted via the submission system.

Special Benefit
DiDi will release a large scale open speech dataset during the workshop. Anyone who has submitted their abstract or paper to the workshop will have early access to the open dataset.

Important dates

Jun. 1, 2020: All invited keynotes and research talks are confirmed.

Sept. 4, 2020: Workshop paper submission due. (Anywhere on Earth)

Sept. 21, 2020: Workshop paper notifications.

Sept. 30, 2020: Workshop camera-ready paper submission.

Oct. 24, 2020: Workshop Day.

Invited Keynote speakers

Jieping Ye (IEEE Fellow, head of Didi AI Tech, VP of Didi Chuxing and Didi Fellow)

Tatsuya Kawahara (IEEE Fellow, Professor of Kyoto University)

Kong Aik Lee (Senior Scientist, Institute for Infocomm Research)

Schedule

9:00 9:10 Opening & Welcome
9:10 9:40 Keynote Talk I
9:40 10:40 Special Session: Target Speaker Aware Speech Synthesis and Voice Conversion
10:45 11:15 AM Keynote Talk II
11:15 12:00 AM Oral Talks I

Break

13:30 14:00 Keynote Talk III
14:00 15:00 Oral Talks II
15:05 15:35 Keynote Talk IV
15:35 16:35 Oral Talks III

Organizers

General Chairs:
Prof. Jieping Ye
Didi Chuxing
University of Michigan

Prof. Longbiao Wang
Tianjin University
Huiyan Technology (Tianjin) CO., LTD.

Technical Program Chairs:
Prof. Jianwu Dang , Tianjin University
Dr. Xiangang Li , Didi Chuxing
Prof. Ming Li , Duke Kunshan University

Local Arrangement Chairs:
Prof. Hui Feng , Tianjin University
Ms. Cheng Gong , Didi Chuxing

Scientific Committee:
Prof. Tatsuya Kawahara , Kyoto University
Prof. Kevin Knight , Didi Chuxing
Prof. Wenju Liu , Institute of Automation, Chinese Academy of Sciences
Prof. Jianhua Tao , Institute of Automation, Chinese Academy of Sciences
Prof. Xihong Wu , Peking University

For inquiries about the workshop and submissions, please email to Interspeech2020_2@yeah.net.