ITG Conference on Speech Communication 

24.-26. September 2025 | Berlin

Scope

The 16^th ITG Conference on Speech Communication will explore the theme of Speech Communication in the Age of Foundation Models. We hope that you will find this an area of pertinent debates and great innovation potential. We are, however, soliciting contributions on all areas of theory, algorithms and applications related to speech, audio, and spoken language processing, comprising especially:

• Foundation Models for Speech Processing 
• Speech Enhancement and Separation
• Source Localization and Tracking
• Detection and Classification of Acoustic Scenes and Events
• Automatic Speech and Speaker Recognition
• Spoken Dialogue, Diarization, and Spoken Document Retrieval Systems
• Speech Synthesis
• Speech Modeling, Coding, and Transmission
• LLMs & Speech Interaction
• Privacy in Speech Technologies
• Speech Production and Perception
• Speech Quality and Intelligibility Assessment
• Paralinguistics, Speech Diagnostics, and Speech‐related Biosignals
• Speech in Automotive, Mobile, and Multimodal Applications
• Acoustic Interfaces, Assistive Devices, and Hearing Aids
• Hardware and Software Tools
• Emerging Topics and Applications
• Self-supervised learning (SSL) from foundation models

Paper Submission and Deadlines

• Registration of Title, Author List and Abstract:       May 23, 2025
• Upload of full paper:                                            May 26, 2025, 23h59 CEST
• Notification of acceptance:                                   July 18, 2025 
• Submission of final print version:                          August 13, 2025

Papers are published by the VDE Verlag at IEEE Xplore, and are expected to be written in English according to the IEEE style guidelines. They must not exceed four pages plus one additional page containing only references. Authors are invited to visit tu.berlin/qu/itg-sc-2025 for details on the submission guidelines.

Technical Program Committee

S. Möller (General Chair), TU Berlin

D. Kolossa (TPC Chair) TU Berlin

T. Gerkmann (General Co-Chair), Univ. Hamburg

C. Antweiler, RWTH Aachen University

S. Doclo, Universität Oldenburg

G. Enzner, Universität Oldenburg

T. Fingscheidt, TU Braunschweig

H.‐W. Gierlich

E. Habets, Int. Audio Laboratories Erlangen

R. Häb‐Umbach, Universität Paderborn

P. Jax, RWTH Aachen University

W. Kellermann, FAU Erlangen‐Nürnberg

D. Klakow, Universität des Saarlandes

R. Koning, Advanced Bionics

G. Kubin, TU Graz

H. Löllmann, FAU Erlangen‐Nürnberg

R. Martin, Ruhr‐Universität Bochum

B. Meyer, Universität Oldenburg

H. Puder, WS Audiology

R. Schlüter, RWTH Aachen University

G. Schmidt, CAU Kiel

B. Schuller, Universität Augsburg

T. Schultz, Universität Bremen

The Author Kit for Interspeech 2025 is now available. Please visit the For Authors section on  https://interspeech2025.org for more information.

A reminder to start thinking about

• ISCA Fellow Nominations for 2025: web page here.
• ISCA Distinguished Lecturer for 2025-26: web page here

Dear colleagues,

the ISCA/ITG Workshop on Diversity in Large Speech and Language Models will be organized by Technische Universität Berlin, Humboldt-Universität zu Berlin and the German Center for Artificial Intelligence (DFKI) Berlin on February 20, 2025 in Berlin, Germany.

Topics which we aim to address include but are not limited to

• User diversity: Which aspects of human speech and language production affect the performance of large foundation models? In which way, and for which tasks?
• Language use: How are large language models able to cope with different languages, dialects, and sociolects? How do they deal with code switching?
• Human adaptation: How does the use of large language models affect language comprehension, as well as speech and language production? Which alignment effects occur, and in which time spans?
• Model adaptation: How do models need to be designed to better cope with speech and language diversity? How do training and finetuning affect model performance?
• Inclusion: What data and technologies are necessary to better cope with diversity in large speech and language models?

We invite both experimental and positional papers addressing these and other related research questions.
The workshop will consist of a number of oral presentations and discussion panels. Accepted speakers are invited to submit a short or long paper which will be published online after the workshop.

Important dates:

• Abstract submission: 13 December 2024
• Notification of acceptance: 10 January 2025
• Short or long paper submission: 14 February 2025

More details can be found here.

Sebastian Möller

Nominations are open for the 2025 ISCA Medal for Scientific Achievement.  Nominations must be submitted by November 1 to ISCA Secretariat at secretariat@isca-speech.org.

We cordially invite all ISCA members to the General Assembly.  We are looking forward to seeing you in Kos.

2024 ISCA General Assembly

Date: Monday September 2, 2024, at 17:30 - 19:30

Venue: Panacea Amphitheater, Kipriotis Hotels & Conference Center (KICC),
      Kos, Greece

ISCA Fellows 2024

The following colleagues have been elected ISCA fellows. Their titles will be conferred formally at Interspeech 2024. congratulations to them!

Takayuki Arai  Dept. of Information and Communication Sciences, Sophia University, Tokyo

For contributions to developing models of speech production and applying them for speech science, technology, pathology and education

Kay Berkling  DHBW Mosbach,  Baden-Wuerttemberg Cooperative State University

For her contributions to education, improving childhood learning and boosting diversity through interactive technology

Carlos Busso  University of Texas at Dallas

For contributions to speech and multimodal affective signal processing and their technology applications

Sebastian Moller    Technische Universität Berlin, and German Research Center for Artificial Intelligence, Berlin

For sustained contributions to the evaluation of speech transmission, processing, and speech technology

Bhiksha Raj  Carnegie Mellon University, Pittsburgh, PA

For contributions to robust speech recognition and other areas in speech and audio processing.

 

Torbjorn Svendsen         NTNU Norwegian University of Science and Technology

  For contributions to speech processing research and long-standing   contributions to the speech community

 

Petra Wagner                    Universität Bielefeld

 For contributions to multimodal prosody, conversational interaction, and speech synthesis.

Dear ISCA member,

Unfortunately, at regular time intervals, e-mails are being send to individuals within our community that seemingly come from the president (or another ISCA board member), asking for help and/or money in vague terms.

Please note, no ISCA board member will ever send emails to ask for money nor would we ask for help in vague terms. If we ask for help it will be clear what we ask of you. If you are unsure whether the email is legit, assume it is not. If we do need your help, we will reach out again.

Unfortunately, there is nothing we can do about this. Please ignore these e-mails.

Best wishes,

Odette Scharenborg, ISCA President

ISCA is currently moving to a new web portal: WildApricot. This includes a new website, and a new portal for membership services. The new website will already be more informative than the old one, and will later enable more active participation from our community (SIGs, etc.), as we want to make it more interactive and target-oriented.

For the time being, parts of our services will still need to be accessed through portals on our old system (linked from the new website), including the paper archive, and applications for workshops and grants. We are working on moving these functionalities to the new platform as well.

Please explore the new website and get an impression of ISCA activities and services. Become involved in shaping the new system for the benefit of our community.

The submission portal for Interspeech 2024, which will take place in Kos, Greece, is now open. The deadline for registering a paper is 2nd of March, for finalising the paper 10th of March. More details on https://interspeech2024.org/.