CHiME-9 Pre-announcement

It gives us great pleasure to pre-announce the 9th CHiME Speech Separation and Recognition Challenge (CHiME-9) that will launch in July 2025.

CHiME-9 TASKS

The CHiME-9 challenge will be composed of two separate tasks:

  • The Multi-Modal Context-aware Recognition (MCoRec) task focuses on accurately transcribing speech from overlapping conversations using both audio and video inputs. Given an audio recording and video footage of participants, the system must differentiate between concurrent conversations and generate a transcription for each conversation. The objective is to answer the question: Who speaks, when, what, and with whom?

  • The Enhancing Conversations to address Hearing Impairment (ECHI) task focuses on enhancing conversational speech for hearing devices. It provides a unique dataset of real conversations recorded with 4-channel hearing aids in a noisy, cafeteria-like environment. We seek low-latency systems that enhance the speech of the hearing device wearer’s conversational partners while suppressing all competing sound sources.

For further task details, see the CHiME Challenge website, https://www.chimechallenge.org/

WORKSHOP

CHiME-9 Challenge submissions will be presented at a 1-day workshop on May 3rd, 2026, that will be organized as a satellite event of ICASSP 2026 (details TBC). The workshop will also be accepting non-challenge papers on related topics. Further details will be posted on the webpage: https://www.chimechallenge.org/

FORUM

If you are considering participating, please join the CHiME Google group for discussions and further announcements. https://groups.google.com/forum/#!forum/chime5/join

IMPORTANT DATES

  • 1 July 2025 Challenge opening
  • 7 Feb 2026 Challenge submission deadline (date and details TBC)
  • 3 May 2026 CHiME 2026, an ICASSP satellite workshop (date and details TBC)

CHiME STEERING GROUP

  • Jon Barker, Univ. of Sheffield, UK
  • Shinji Watanabe, Carnegie Mellon Univ., USA
  • Michael Mandel, CUNY/META, USA
  • Marc Delcroix, NTT, Japan
  • Leibny Paola, Garcia Perera Johns Hopkins Univ., USA

MCoRec TASK ORGANIZERS

  • Alexander Waibel (CMU, USA & KIT, DE),
  • Christian Fuegen (Meta, UK),
  • Shinji Watanabe (CMU, USA)
  • Katerina Zmolikova (Meta, UK),
  • Thai-Binh Nguyen (KIT, DE),
  • Pingchuan Ma (Meta, USA)

ECHI TASK ORGANIZERS

  • Jon Barker (University of Sheffield, UK),
  • Stefan Goetze (University of Sheffield, UK),
  • Robert Sutherland (University of Sheffield, UK),
  • Marko Lugger (WSAudiology),
  • Thomas Kuebert (WSAudiology),
  • Stefan Petrausch (WSAudiology)