一种用于微调面向口语理解的多语言语义语音编码器的双任务学习方法
A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding
AI总结：
针对SAMU-XLSR框架专门化训练导致多语言性能下降、单独SLU微调丧失跨语言能力的问题，本文提出双任务学习方法，结合远距离语言实验提升其语义增强效果与语言可移植性。
摘要：
自监督学习（Self-Supervised Learning）被广泛用于为口语理解（Spoken Language Understanding，SLU）高效生成语音表示，正逐步取代传统方法。同时，文本自监督学习模型被提出用于编码语言无关的语义。SAMU-XLSR框架利用这类语义信息来丰富多语言语音表示。近期一项研究通过让SAMU-XLSR在下游转录任务上进行 specialization（专门化训练），探究了其域内语义增强效果，在一项具有挑战性的SLU任务上取得了当前最优结果。本研究关注的问题是：在无SLU相关标注的相近语言中进行这类专门化训练，会导致多语言性能下降，且缺乏特定语义训练。我们还考虑到，单独的SLU微调会导致SAMU-XLSR丧失初始的跨语言能力。因此，本文提出一种双任务学习方法，在引入远距离语言开展多语言及语言可移植性实验的同时，提升SAMU-XLSR的语义增强效果。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
