adima

Abuse Detection In Multilingual Audio

https://github.com/sharechatai/adima

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (7.7%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Abuse Detection In Multilingual Audio

Basic Info
  • Host: GitHub
  • Owner: ShareChatAI
  • License: other
  • Language: Python
  • Default Branch: main
  • Size: 20.5 KB
Statistics
  • Stars: 5
  • Watchers: 1
  • Forks: 2
  • Open Issues: 0
  • Releases: 0
Created over 4 years ago · Last pushed about 4 years ago
Metadata Files
Readme License Citation

README.md

Adima

This is an official pytorch implementation of our ICASSP 2022 paper ADIMA: ABUSE DETECTION IN MULTILINGUAL AUDIO.

In this repository, we provide the dataset and codebase for exploring our work.

Please visit the Project Page for more details about the dataset.

ADIMA Dataset

Audio files and annotations of ADIMA can be downloaded from here.

The annotation folder contains the train and test splits used in our paper for all the languages. Each row of the csv contains the name of audio file and ground-truth indicating the presence of profanity.

For example, “Hinditrain.csv” and “Hinditest.csv” contains the train and test data for Hindi language.

Each row of this file has the name of audio file and its label. Labels “Yes” and “No” represent the presence and absence of profanity in the audio file.

Codebase

Please refer to the instructions shared in the train folder.

BibTeX Citation

If you find ADIMA useful in your research, please use the following BibTeX entry for citation.

@inproceedings{gupta2022adima, title={ADIMA: Abuse Detection In Multilingual Audio}, author={Gupta, Vikram and Sharon, Rini and Sawhney, Ramit and Mukherjee, Debdoot}, booktitle={ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages={6172--6176}, year={2022}, organization={IEEE} }

Owner

  • Login: ShareChatAI
  • Kind: user

Citation (CITATION.cff)

@inproceedings{gupta2022adima,
  title={ADIMA: Abuse Detection In Multilingual Audio},
  author={Gupta, Vikram and Sharon, Rini and Sawhney, Ramit and Mukherjee, Debdoot},
  booktitle={ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={6172--6176},
  year={2022},
  organization={IEEE}
}

GitHub Events

Total
  • Fork event: 1
Last Year
  • Fork event: 1