mlsanityData to 7 Oct 2026

Improving Spoken Language Identification with Map-Mix

arXiv 2302.08229 ↗First posted 16 Feb 2023cs.LG cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

The pre-trained multi-lingual XLSR model generalizes well for language identification after fine-tuning on unseen languages. However, the performance significantly degrades when the languages are not very distinct from each other, for example, in the case of dialects. Low resource dialect classification remains a challenging problem to solve. We present a new data augmentation method that leverages model training dynamics of individual data points to improve sampling for latent mixup. The method works well in low-resource settings where generalization is paramount. Our datamaps-based mixup technique, which we call Map-Mix improves weighted F1 scores by 2% compared to the random mixup baseline and results in a significantly well-calibrated model. The code for our method is open sourced on https://github.com/skit-ai/Map-Mix.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 23 references that are in the map. First posted on arXiv 16 Feb 2023.

Builds on

14 of 23 references.

References · 14

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  4. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  5. 2019When Does Label Smoothing Help?cited by 985
  6. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 589
  7. 2020Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamicscited by 423
  8. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  9. 2020MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classificationcited by 186
  10. 2020Exploring wav2vec 2.0 on speaker verification and language identificationcited by 93
  11. 2021MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognitioncited by 38
  12. 2022On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliencycited by 31
2 more
  1. 2021Improved Language Identification Through Cross-Lingual Self-Supervised Learningcited by 20
  2. 2018Deep Convolutional Neural Network with Mixup for Environmental Sound Classificationcited by 15

Built on by

Not cited yet.