Skip to content

The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to provide participants with baseline systems for speech recognition and speaker diarization in conference scenario.

Notifications You must be signed in to change notification settings

yufan-aslp/AliMeeting

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

M2MeT challenge baseline -- AliMeeting

This project provides the baseline system recipes for the ICASSP 2020 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT). The challenge mainly consists of two tracks, named Automatic Speech Recognition (ASR) and Speaker Diarization. For each track, detailed descriptions can be found in its corresponding directory. The goal of this project is to simplify the training and evaluation procedures and make it flexible for participants to reproduce the baseline experiments and develop novelty methods.

Setup

git clone https://github.com/yufan-aslp/AliMeeting.git

Introduction

General steps

  1. Prepare the training data for speaker diarization and ASR model, respectively
  2. Follow the running steps of the speaker diarization experiment and obtain the rttm file. The rttm file includes the voice activity detection (VAD) and speaker diarization results, which will be used to compute the final Diarization Error Rate (DER) scores.
  3. For ASR track, we can train the single-speaker or multi-speaker ASR models. The evaluation metric of ASR systems is Character Error Rate (CER).

Citation

If you use the challenge dataset or our baseline systems, please consider citing the following:

@inproceedings{Yu2022M2MeT,
  title={M2{M}e{T}: The {ICASSP} 2022 Multi-Channel Multi-Party Meeting Transcription Challenge},
  author={Yu, Fan and Zhang, Shiliang and Fu, Yihui and Xie, Lei and Zheng, Siqi and Du, Zhihao and Huang, Weilong and Guo, Pengcheng and Yan, Zhijie and Ma, Bin and Xu, Xin and Bu, Hui},
  booktitle={Proc. ICASSP},
  year={2022},
  organization={IEEE}
}

@inproceedings{Yu2022Summary,
  title={Summary On The {ICASSP} 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge},
  author={Yu, Fan and Zhang, Shiliang and Guo, Pengcheng and Fu, Yihui and Du, Zhihao and Zheng, Siqi and Huang, Weilong and Xie, Lei  and Tan, Zheng-Hua and Wang, DeLiang and Qian, Yanmin and Lee, Kong Aik and Yan, Zhijie and Ma, Bin and Xu, Xin and Bu, Hui},
  booktitle={Proc. ICASSP},
  year={2022},
  organization={IEEE}
}

Challenge introduction paper: M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge (https://arxiv.org/abs/2110.07393?spm=a3c0i.25445127.6257982940.1.111654811kxLMY&file=2110.07393)

Challenge summary paper: Summary On The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge (https://arxiv.org/abs/2202.03647?spm=a3c0i.25445127.6257982940.2.111654811kxLMY&file=2202.03647)

The AliMeeting data download at https://www.openslr.org/119

Room config of AliMeeting Train set download at https://speech-lab-share-data.oss-cn-shanghai.aliyuncs.com/AliMeeting/AliMeeting_Trainset_Room.xlsx

M2MeT challege codalab(Open evaluation platform for Eval and Test sets of both Tracks): https://codalab.lisn.upsaclay.fr/competitions/?q=M2MeT

Organizing Committee

Contributors

Code license

Apache 2.0

About

The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to provide participants with baseline systems for speech recognition and speaker diarization in conference scenario.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published