English

Label Aware Speech Representation Learning For Language Identification

Computation and Language 2023-06-08 v1 Machine Learning Sound Audio and Speech Processing

Abstract

Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model or self-supervised representation learning approaches using raw data. In this paper, we propose a novel framework of combining self-supervised representation learning with the language label information for the pre-training task. This framework, termed as Label Aware Speech Representation (LASR) learning, uses a triplet based objective function to incorporate language labels along with the self-supervised loss function. The speech representations are further fine-tuned for the downstream task. The language recognition experiments are performed on two public datasets - FLEURS and Dhwani. In these experiments, we illustrate that the proposed LASR framework improves over the state-of-the-art systems on language identification. We also report an analysis of the robustness of LASR approach to noisy/missing labels as well as its application to multi-lingual speech recognition tasks.

Keywords

Cite

@article{arxiv.2306.04374,
  title  = {Label Aware Speech Representation Learning For Language Identification},
  author = {Shikhar Vashishth and Shikhar Bharadwaj and Sriram Ganapathy and Ankur Bapna and Min Ma and Wei Han and Vera Axelrod and Partha Talukdar},
  journal= {arXiv preprint arXiv:2306.04374},
  year   = {2023}
}

Comments

Accepted at Interspeech 2023

R2 v1 2026-06-28T10:58:45.687Z