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

TL;DR

This paper introduces a dual task learning method to enhance a multilingual speech encoder's semantic understanding, aiming to improve performance across diverse languages without sacrificing cross-lingual capabilities.

Contribution

It proposes a novel dual task learning approach that balances semantic enrichment and multilingual performance in speech encoders, addressing limitations of previous specialization methods.

Findings

Improved semantic enrichment across multiple languages.

Maintained cross-lingual abilities after fine-tuning.

Enhanced performance on multilingual SLU tasks.

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.