Skip to main content Link Menu Expand (external link) Document Search Copy Copied

CHiME-2023 Workshop

This one-day workshop will bring together researchers from the fields of speech enhancement, speech and speaker recognition, computational hearing, and machine learning to discuss the robustness of speech processing in everyday environments, i.e., real-world conditions with acoustic clutter, where the number and nature of the sound sources is unknown and changing over time. Relevant research topics include (but are not limited to)

  • training schemes: data simulation and augmentation, semi-supervised training,
  • speaker identification and diarization,
  • speaker localization and beamforming,
  • single- or multi-microphone enhancement and separation,
  • robust features and feature transforms,
  • robust acoustic and language modeling,
  • traditional or end-to-end robust speech recognition,
  • robust speaker and language recognition,
  • robust paralinguistics,
  • cross-environment or cross-dataset performance analysis,
  • environmental background noise modelling.

Papers reporting evaluation results on the CHiME-6 dataset or on other datasets are equally welcome.

The CHiME-7 Challenges

As a focus for discussion, the workshop will host the 7th CHiME Speech Separation and Recognition Challenge (CHiME-7) made up of two tasks:

  • The first task (CHiME-7 DASR) focuses on distant automatic speech transcription and segmentation with multiple recording devices, especially on generalization across different array topologies.

  • The second task (CHiME-7 UDASE) focuses on unsupervised domain adaptation for conversational speech enhancement. It involves learning to suppress noise in multi-speaker conversational speech recordings using out-of-domain labeled data and in-domain unlabeled data.


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

More information

Keynote Speakers

Stay tuned for updated speakers


1 Feb 2023 Challenge opening
30 June 2023 Challenge submission deadline
25 Aug 2023 Interspeech satellite workshop (details TBC)

More information

Table of contents