Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning
Not on the map. Why?
Abstract (arXiv)
Online abusive content detection, particularly in low-resource settings and within the audio modality, remains underexplored. We investigate the potential of pre-trained audio representations for detecting abusive language in low-resource languages, in this case, in Indian languages using Few Shot Learning (FSL). Leveraging powerful representations from models such as Wav2Vec and Whisper, we explore cross-lingual abuse detection using the ADIMA dataset with FSL. Our approach integrates these representations within the Model-Agnostic Meta-Learning (MAML) framework to classify abusive language in 10 languages. We experiment with various shot sizes (50-200) evaluating the impact of limited data on performance. Additionally, a feature visualization study was conducted to better understand model behaviour. This study highlights the generalization ability of pre-trained models in low-resource scenarios and offers valuable insights into detecting abusive language in multilingual contexts.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 54 references that are in the map. First posted on arXiv 2 Dec 2024.
Builds on
30 of 54 references.
References · 30
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 563
- 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
- 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
- 2021MuRIL: Multilingual Representations for Indian Languagescited by 177
- 2020Contrastive Learning of General-Purpose Audio Representationscited by 168
- 2018Meta-Learning for Low-Resource Neural Machine Translationcited by 105
18 more
- 2019A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Mediacited by 95
- 2022BYOL for Audio: Exploring Pre-trained General-purpose Audio Representationscited by 36
- 2021Exploiting Adapters for Cross-lingual Low-resource Speech Recognitioncited by 33
- 2021Universal Paralinguistic Speech Representations Using Self-Supervised Conformerscited by 32
- 2022Few-Shot Classification with Contrastive Learningcited by 31
- 2019Meta Learning for End-to-End Low-Resource Speech Recognitioncited by 29
- 2021Multilingual Offensive Language Identification for Low-resource Languagescited by 22
- 2021CLSRIL-23: Cross Lingual Speech Representations for Indic Languagescited by 22
- 2021MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learningcited by 21
- 2022Emotion Based Hate Speech Detection using Multimodal Learningcited by 18
- 2021Multilingual and cross-lingual document classification: A meta-learning approachcited by 14
- 2024MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detectorcited by 14
- 2021DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterancescited by 13
- 2022ADIMA: Abuse Detection In Multilingual Audiocited by 11
- 2023Model-Agnostic Meta-Learning for Multilingual Hate Speech Detectioncited by 11
- 2022Improved Meta Learning for Low Resource Speech Recognitioncited by 7
- 2024Abusive Speech Detection in Indic Languages Using Acoustic Featurescited by 2
- 2024CoLLAB: A Collaborative Approach for Multilingual Abuse Detectioncited by 1
Built on by
Not cited yet.