Abstract

Directly translating from speech to text using an end-to-end approach is still challenging for many language pairs due to insufficient data. Although pretraining the encoder parameters using the Automatic Speech Recognition (ASR) task improves the results in low resource settings, attempting to use pretrained parameters from the Neural Machine Translation (NMT) task has been largely unsuccessful in previous works. In this paper, we will show that by using an adversarial regularizer, we can bring the encoder representations of the ASR and NMT tasks closer even though they are in different modalities, and how this helps us effectively use a pretrained NMT decoder for speech translation.

Highlights

  • Automatic Speech Translation (AST) aims to directly translate audio signals in the source language into the text words in the target language

  • We analyze the effect of our regularizer on two different settings: (A) When we only have access to AST data and (B) When we can benefit from External data

  • Adding external data can boost the performance of the cascaded model and by comparing Table 2 and 3, we can see that the additional Neural Machine Translation (NMT) and Automatic Speech Recognition (ASR) data can improve the translation quality of the cascaded model by +2 BLEU scores, while it can barely affect the AST model with pretrained encoder and the decoder

Read more

Summary

Introduction

Automatic Speech Translation (AST) aims to directly translate audio signals in the source language into the text words in the target language. While pretraining the encoder by an ASR model even in different languages shows promising results (Bansal et al, 2019), using a pretrained MT decoder is not beneficial (Berard et al, 2018; Bansal et al, 2018) or slightly improve the result (Sperber et al, 2019) and even in some cases may worsen the results (Bahar et al, 2019) One explanation for this phenomenon is that the decoder works well only if its input comes from an encoder that it was trained with (Lample et al, 2018). We show that this modification can improve the BLEU score by +2.0 BLEU points

End-to-End Speech Translation
Adversarial regularizer
Aligning encoder representations
Dataset
Preprocessing and Evaluation
Training settings
Model settings
Results
Using only AST data
Using both AST and External data
Related Work
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.