Robust Neural Machine Translation for Clean and Noisy Speech Transcripts

10/22/2019
by   Mattia Antonino Di Gangi, et al.
0

Neural machine translation models have shown to achieve high quality when trained and fed with well structured and punctuated input texts. Unfortunately, the latter condition is not met in spoken language translation, where the input is generated by an automatic speech recognition (ASR) system. In this paper, we study how to adapt a strong NMT system to make it robust to typical ASR errors. As in our application scenarios transcripts might be post-edited by human experts, we propose adaptation strategies to train a single system that can translate either clean or noisy input with no supervision on the input type. Our experimental results on a public speech translation data set show that adapting a model on a significant amount of parallel data including ASR transcripts is beneficial with test data of the same type, but produces a small degradation when translating clean text. Adapting on both clean and noisy variants of the same data leads to the best results on both input types.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/25/2019

Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training

In a pipeline speech translation system, automatic speech recognition (A...
research
11/02/2018

Improving the Robustness of Speech Translation

Although neural machine translation (NMT) has achieved impressive progre...
research
04/24/2019

Assessing the Tolerance of Neural Machine Translation Systems Against Speech Recognition Errors

Machine translation systems are conventionally trained on textual resour...
research
10/07/2019

Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation

Neural Machine Translation (NMT) models have been proved strong when tra...
research
02/26/2021

Gradient-guided Loss Masking for Neural Machine Translation

To mitigate the negative effect of low quality training data on the perf...
research
04/13/2021

Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding

Spoken language understanding (SLU) system usually consists of various p...
research
06/03/2019

Dynamically Composing Domain-Data Selection with Clean-Data Selection by "Co-Curricular Learning" for Neural Machine Translation

Noise and domain are important aspects of data quality for neural machin...

Please sign up or login with your details

Forgot password? Click here to reset