It has been known that direct speech-to-speech translation (S2ST) models usually suffer from the data scarcity issue because of the limited existing parallel materials for both source and target speech. Therefore to train a direct S2ST system, previous works usually utilize text-to-speech (TTS) systems to generate samples in the target language by augmenting the data from speech-to-text translation (S2TT). However, there is a limited investigation into how the synthesized target speech would affect the S2ST models. In this work, we analyze the effect of changing synthesized target speech for direct S2ST models. We find that simply combining the target speech from different TTS systems can potentially improve the S2ST performances. Following that, we also propose a multi-task framework that jointly optimizes the S2ST system with multiple targets from different TTS systems. Extensive experiments demonstrate that our proposed framework achieves consistent improvements (2.8 BLEU) over the baselines on the Fisher Spanish-English dataset.
翻译:已知,直接语音到语音翻译 (S2ST) 模型常常因为源语音和目标语音的有限平行语料库而遭受数据匮乏的问题。因此,在训练直接 S2ST 系统时,先前的研究通常利用文本到语音 (TTS) 系统通过从语音到文本翻译 (S2TT) 增广目标语言的数据来生成样本。然而,对合成的目标语音如何影响 S2ST 模型的研究很有限。在这项工作中,我们分析了更改直接 S2ST 模型的合成目标语音的影响。我们发现,简单地组合来自不同 TTS 系统的目标语音可能会提高 S2ST 的性能。随后,我们还提出了一个多任务框架,它以不同 TTS 系统的多个目标语音为优化直接 S2ST 系统的联合目标。广泛的实验证明,我们提出的框架在 Fisher 西班牙语-英语数据集上相对于基线实现了一致的改善 (2.8 BLEU)。