Abusive Speech Detection in Indic Languages Using Acoustic Features
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911972109320192 |
|---|---|
| author | Spiesberger, Anika A. Triantafyllopoulos, Andreas Tsangko, Iosif Schuller, Björn W. |
| author_facet | Spiesberger, Anika A. Triantafyllopoulos, Andreas Tsangko, Iosif Schuller, Björn W. |
| contents | Abusive content in online social networks is a well-known problem that can cause serious psychological harm and incite hatred. The ability to upload audio data increases the importance of developing methods to detect abusive content in speech recordings. However, simply transferring the mechanisms from written abuse detection would ignore relevant information such as emotion and tone. In addition, many current algorithms require training in the specific language for which they are being used. This paper proposes to use acoustic and prosodic features to classify abusive content. We used the ADIMA data set, which contains recordings from ten Indic languages, and trained different models in multilingual and cross-lingual settings. Our results show that it is possible to classify abusive and non-abusive content using only acoustic and prosodic features. The most important and influential features are discussed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20808 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Abusive Speech Detection in Indic Languages Using Acoustic Features Spiesberger, Anika A. Triantafyllopoulos, Andreas Tsangko, Iosif Schuller, Björn W. Sound Audio and Speech Processing Abusive content in online social networks is a well-known problem that can cause serious psychological harm and incite hatred. The ability to upload audio data increases the importance of developing methods to detect abusive content in speech recordings. However, simply transferring the mechanisms from written abuse detection would ignore relevant information such as emotion and tone. In addition, many current algorithms require training in the specific language for which they are being used. This paper proposes to use acoustic and prosodic features to classify abusive content. We used the ADIMA data set, which contains recordings from ten Indic languages, and trained different models in multilingual and cross-lingual settings. Our results show that it is possible to classify abusive and non-abusive content using only acoustic and prosodic features. The most important and influential features are discussed. |
| title | Abusive Speech Detection in Indic Languages Using Acoustic Features |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.20808 |