mlsanityData to 7 Oct 2026

Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili

arXiv 2306.00410 ↗First posted 1 Jun 2023cs.CL cs.SD eess.AScited by 5

Not on the map. Why?

Abstract (arXiv)

We consider hate speech detection through keyword spotting on radio broadcasts. One approach is to build an automatic speech recognition (ASR) system for the target low-resource language. We compare this to using acoustic word embedding (AWE) models that map speech segments to a space where matching words have similar vectors. We specifically use a multilingual AWE model trained on labelled data from well-resourced languages to spot keywords in data in the unseen target language. In contrast to ASR, the AWE approach only requires a few keyword exemplars. In controlled experiments on Wolof and Swahili where training and test data are from the same domain, an ASR model trained on just five minutes of data outperforms the AWE approach. But in an in-the-wild test on Swahili radio broadcasts with actual hate speech keywords, the AWE model (using one minute of template data) is more robust, giving similar performance to an ASR system trained on 30 hours of labelled data.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 22 of its 36 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

22 of 36 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  4. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 589
  5. 2021Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Trainingcited by 148
  6. 2020Rethinking Evaluation in ASR: Are Our Models Robust Enough?cited by 72
  7. 2016Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencodercited by 34
  8. 2018Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder modelscited by 29
  9. 2015Deep convolutional acoustic word embeddings using word-pair side informationcited by 27
  10. 2016Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approachescited by 25
  11. 2017Query-by-Example Search with Discriminative Neural Acoustic Word Embeddingscited by 22
  12. 2017End-to-End ASR-free Keyword Search from Speechcited by 19
10 more
  1. 2021Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptationcited by 19
  2. 2020Multilingual Jointly Trained Acoustic and Written Word Embeddingscited by 16
  3. 2019Semantic query-by-example speech search using visual groundingcited by 11
  4. 2020Improved acoustic word embeddings for zero-resource languages using multilingual transfercited by 11
  5. 2019Neural Network based End-to-End Query by Example Spoken Term Detectioncited by 8
  6. 2021Do Acoustic Word Embeddings Capture Phonological Similarity? An Empirical Studycited by 8
  7. 2018Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoringcited by 7
  8. 2020Acoustic span embeddings for multilingual query-by-example searchcited by 7
  9. 2021Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource languagecited by 7
  10. 2021Feature learning for efficient ASR-free keyword spotting in low-resource languagescited by 6

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 3.

5 papers.

  1. 2025Automatic Speech Recognition for African Low-Resource Languages: Challenges and Future Directionscited by 6
  2. 2024Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representationscited by 3
  3. 2023Leveraging multilingual transfer for unsupervised semantic acoustic word embeddingscited by 2
  4. 2025Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Reviewcited by 2
  5. 2025Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Researchcited by 0