Speech Processing in Everyday Environments (CHiME 2020)

4th May, Virtual Workshop

The workshop is now over. For a full record of the event, including links to YouTube videos, slides and abstracts, please see the programme page.

This one-day virtual 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-6 Challenge

As a focus for discussion, the workshop will host the 6th CHiME Speech Separation and Recognition Challenge (CHiME-6). The challenge will consider the problem of conversational speech recognition and diarization in everyday home environments from multiple distant microphone arrays. It will be using a resychronized version of the Dinner Party speech data featured in CHiME-5 and will have two tracks: a rerun of the CHiME-5 multi-array ASR task; and a new joint diarization and ASR task. To find out more please visit the Challenge website.

CHiME 2020 Virtual Workshop

Organisers

• Jon Barker
  Univ. of Sheffield, UK
• Emmanuel Vincent
  Inria, France
• Shinji Watanabe
  Johns Hopkins Univ., USA
• Michael Mandel CUNY, USA
• More info

Local Organisers

• Joan Serrà Dolby Laboratories, Barcelona
• Mireia Farrús Universitat Pompeu Fabra (UPF)

Keynote Speakers

• Paola García Johns Hopkins University
• Dong Yu Tencent AI Lab

Dates

• Regular paper submission: Mar 20th
• Notification: Apr 6th
• Challenge submission: Apr 10th
• Workshop: May 4th
• More info