English

A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding

Computation and Language 2024-06-19 v1 Sound Audio and Speech Processing

Abstract

Self-Supervised Learning is vastly used to efficiently represent speech for Spoken Language Understanding, gradually replacing conventional approaches. Meanwhile, textual SSL models are proposed to encode language-agnostic semantics. SAMU-XLSR framework employed this semantic information to enrich multilingual speech representations. A recent study investigated SAMU-XLSR in-domain semantic enrichment by specializing it on downstream transcriptions, leading to state-of-the-art results on a challenging SLU task. This study's interest lies in the loss of multilingual performances and lack of specific-semantics training induced by such specialization in close languages without any SLU implication. We also consider SAMU-XLSR's loss of initial cross-lingual abilities due to a separate SLU fine-tuning. Therefore, this paper proposes a dual task learning approach to improve SAMU-XLSR semantic enrichment while considering distant languages for multilingual and language portability experiments.

Keywords

Cite

@article{arxiv.2406.12141,
  title  = {A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding},
  author = {Gaëlle Laperrière and Sahar Ghannay and Bassam Jabaian and Yannick Estève},
  journal= {arXiv preprint arXiv:2406.12141},
  year   = {2024}
}

Comments

In Proceedings of Interspeech 2024

R2 v1 2026-06-28T17:09:38.066Z