Multilingual End-to-End Speech Translation

Abstract

In this paper, we propose a simple yet effective framework for multilingual end-to-end speech translation (ST), in which speech utterances in source languages are directly translated to the desired target languages with a universal sequence-to-sequence architecture. While multilingual models have shown to be useful for automatic speech recognition (ASR) and machine translation (MT), this is the first time they are applied to the end-to-end ST problem. We show the effectiveness of multilingual end-to-end ST in two scenarios: one-to-many and many-to-many translations with publicly available data. We experimentally confirm that multilingual end-to-end ST models significantly outperform bilingual ones in both scenarios. The generalization of multilingual training is also evaluated in a transfer learning scenario to a very low-resource language pair. All of our codes and the database are publicly available to encourage further research in this emergent multilingual ST topic.

Accepted to ASRU 2019

References in corpus (6)

• ADADELTA: An Adaptive Learning Rate Method
• Recurrent Neural Network Regularization
• Attention-Based Models for Speech Recognition
• Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder
• Effective Strategies in Zero-Shot Neural Machine Translation
• End-to-End Speech Translation with Knowledge Distillation

Cited by in corpus (1)

• Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation