论文标题
代码切换语音的端到端语音翻译
End-to-End Speech Translation for Code Switched Speech
论文作者
论文摘要
代码切换（CS）是指使用不同语言的单词和短语互换的现象。由于基础系统的通常单语性，CS可能对NLP构成重大准确的挑战。在这项工作中，我们在英语/西班牙对话的背景下专注于语音翻译任务（ST），生成和评估成绩单和翻译。为了评估该任务上的模型性能，我们创建了一个新颖的ST语料库，该新颖的语料库源自现有的公共数据集。我们探索跨两个维度的各种ST体系结构：级联（转录然后翻译）与端到端（共同转录和翻译）和单向（源 - >目标）与双向（源<-> target）。我们表明，即使没有使用CS培训数据，我们的ST体系结构，尤其是我们的双向端到端体系结构，在CS语音上表现良好。
Code switching (CS) refers to the phenomenon of interchangeably using words and phrases from different languages. CS can pose significant accuracy challenges to NLP, due to the often monolingual nature of the underlying systems. In this work, we focus on CS in the context of English/Spanish conversations for the task of speech translation (ST), generating and evaluating both transcript and translation. To evaluate model performance on this task, we create a novel ST corpus derived from existing public data sets. We explore various ST architectures across two dimensions: cascaded (transcribe then translate) vs end-to-end (jointly transcribe and translate) and unidirectional (source -> target) vs bidirectional (source <-> target). We show that our ST architectures, and especially our bidirectional end-to-end architecture, perform well on CS speech, even when no CS training data is used.
