Fall 2024 Edition of the Speech and Language Processing Technical Committee (SLTC) Newsletter

Welcome to the Fall 2024 Edition of the Speech and Language Processing Technical Committee (SLTC) Newsletter.  

 

We have collected several updates for this edition, covering an update from the SPS challenge program, member elections, recognizing ICASSP reviewers, and news about upcoming conferences & workshops.

 

==SPS Challenge Program==

by Jun Du

 

For ICASSP 2025, four grand challenges related to SLTC are accepted (https://2025.ieeeicassp.org/sp-grand-challenges/):

• - MEIJU-The 1st Multimodal Emotion and Intent Joint Understanding Challenge
• - The Prediction and Recognition Of Cognitive declinE through Spontaneous Speech (PROCESS) Signal Processing Grand Challenge
• - The First VoicePrivacy Attacker Challenge
• - Multilingual streaming TTS with neural codecs for Indian languages

 

==Member Election==

by Ebru Arisoy

The Member Election Subcommittee of the SLTC is pleased to announce the results of the election for members serving the 2025-2027 term. This year, we had 16 openings across 8 areas, considering retirements and recent ICASSP trends. We received nominations from a total of 44 candidates.

Without further ado, the newly (re)elected members are:

Dialog Systems (1) — Ryuichiro Higashinaka
Natural Language Processing (4) — Xie Chen, William Hartmann**, Atsunori Ogawa, Sibel Oyman**
Speaker Recognition (1)  — Jiangyan Yi
Speech Analysis (1) — Carlos Busso
Speech Enhancement (2) — Daniele Giacobello**, Emanuël Habets**
Speech Recognition (4)
    Acoustic Modeling —  Takashi Fukuda, Yanmin Qian**
    Other — Naoyuki Kanda, Karen Livescu
Speech Synthesis/Generation (3) — Qiong Hu**, Berrak Sisman**, Shinnosuke Takamichi

**reelected member

Congratulations to all (9 new members and 7 re-elected members, listed in alphabetical order within each category), and many thanks to everyone who was willing to serve on the Committee and run in the election. We look forward to working with all of you.

 

 

==Conference Support==

by Rohit Prabhavalkar

 

The conference support subcommittee recently helped the ICASSP2025 recruit 81 new reviewer candidates.

 

==External Relations==

by Hung-yi Lee

 

Since May 2024, the External Relations Subcommittee has been running the "Webinar Series for Advancements in Audio, Speech, and Language Technology" in collaboration with the IEEE SPS Education Center and the IEEE AASP Technical Committee. We strive to host at least one speaker each month (with the exception of September, when many are attending INTERSPEECH).

 

Below, you will find a list of this year's speakers. We extend our heartfelt thanks to all who have given talks and shared their knowledge. We are excited to continue the Webinar Series into next year. If you receive an invitation from us, please accept it. Additionally, if any SLTC members have insights or experiences to share, we welcome your volunteer participation!

 

Below, please find the list of speakers:

 

Jinyu Li

Title: End-to-End Automatic Speech Recognition

Time: May 10, 2024 @ 1:00 pm EDT

 

Meinard Müller

Title: Nonnegative Autoencoders with Applications to Music Audio Decomposing

Time: May 14, 2024 @ 8:00 am EDT

 

Marc Delcroix

Title: Neural Target Speech and Sound Extraction: An Overview

Time: June 6, 2024 @ 7:30 pm EDT

 

Timo Gerkmann

Title:  Diffusion Models for Speech Enhancement and Restoration

Time: June 19, 2024 @ 8:30 am EDT

 

Takuya Yoshioka

Title: Conversational Speech Processing and Recognition: Speech Separation, End-to-End Modeling, and Speaker Diarization

Time: July 23, 2024 @ 1:00 pm EDT

 

Abdelrahman Mohamed, Hung-yi Lee, Shinji Watanabe, Tara N. Sainath, Karen Livescu, Shang-Wen Li, Katrin Kirchhoff

Title: The Changing Landscape of Speech Foundation Models

Time: August 6, 2024 @ 1:00 pm EDT

 

Dan Stowell

Title: Computational Bioacoustics: Signal Processing & Pattern Recognition of Animal Sounds

Time: October 4, 2024 @ 1:00 pm EDT

 

Tomohiro Nakatani

Title: Enhancing Speech Quality: Modern Techniques in Dereverberation

Time: November 14, 2024 @ 7:30 am EDT

 

Hung-yi Lee  

Title: Teaching Foundation Models New Skills: Insights and Experiences

Time:  December 17, 2024 @ 10:00 am EDT

 

 

==Conferences, Workshops and Call for Papers==

by Zhijian Ou

 

2024 IEEE Spoken Language Technology Workshop

 

The 2024 IEEE Spoken Language Technology Workshop (SLT 2024) will be held on December 2nd – 5th, 2024, in Macao, China. The SLT Workshop is a flagship event of the IEEE Speech and Language Processing Technical Committee and is held every two years. It serves as a platform for researchers from academia and industry to discuss shared challenges in the fields of automatic speech recognition and understanding. We warmly invite participants to the workshop.

 

There will be 4 keynote speakers and 3 invited speeches; they are

 

 

• Mark Hasegawa-Johnson from the University of Illinois, USA

• Jianhua Tao from Tsinghua University, China

• Junlan Feng from China Mobile, China

• Preslav Nakov from Mohamed bin Zayed University of Artificial Intelligence

• Satoshi Nakamura from the Chinese University of Hong Kong, Shenzhen, China

• Tara N. Sainath from Google, USA

• Wenwu Wang from University of Surrey, UK

 

Program overview: https://2024.ieeeslt.org/program/

 

Detailed program: https://2024.ieeeslt.org/detailed-schedule/

 

To learn more about Macao: https://2024.ieeeslt.org/about-macao/

 

The Organizing Committee would like to invite your participation in this event. You will have the opportunity to interact with academic researchers, industrial developers, and top-notch postgraduate students in research fields. Your participation will increase your organization’s visibility in the spoken language processing community.

 

 

This newsletter is an ideal forum for updates, reports, announcements, and editorials that don't fit well with traditional journals. We welcome your contributions, as well as calls for papers, job announcements, comments, and suggestions. You can submit job postings here, contact the TC via this form, or send an email to speechnewseds@listserv.ieee.org to propose articles. To subscribe to the Newsletter, send an email with the command "subscribe speechnewsdist" in the message body to listserv@listserv.ieee.org.

 

If you want to stay connected to the IEEE SLTC between newsletters, we are on Twitter @IEEE_SLTC.

 

From all of us: Stay safe and do good.

 

Engin Erzin, Editor 

Leibny Paola Garcia Perera, Communications Vice-Chair