System Description on Automatic Simultaneous Translation Workshop

This paper shows our submission on the second automatic simultaneous translation workshop at NAACL2021. We participate in all the two directions of Chinese-to-English translation, Chinese audio\rightarrowEnglish text and Chinese text\rightarrowEnglish text. We do data filtering and model training techniques to get the best BLEU score and reduce the average lagging. We propose a two-stage simultaneous translation pipeline system which is composed of Quartznet and BPE-based transformer. We propose a competitive simultaneous translation system and achieves a BLEU score of 24.39 in the audio input track.

[1]  Xing Li,et al.  STACL: Simultaneous Translation with Integrated Anticipation and Controllable Latency , 2018, ArXiv.

[2]  Akshay Krishna Sheshadri,et al.  WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm , 2021, ArXiv.

[3]  Hua Wu,et al.  BSTC: A Large-Scale Chinese-English Speech Translation Dataset , 2021, AUTOSIMTRANS.

[4]  Alexander M. Rush,et al.  OpenNMT: Open-Source Toolkit for Neural Machine Translation , 2017, ACL.

[5]  Boris Ginsburg,et al.  Jasper: An End-to-End Convolutional Neural Acoustic Model , 2019, INTERSPEECH.

[6]  Boris Ginsburg,et al.  Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions , 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[7]  Philipp Koehn,et al.  Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[8]  André F. T. Martins,et al.  Marian: Fast Neural Machine Translation in C++ , 2018, ACL.

[9]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[10]  Ke Sun,et al.  Chinese Lexical Analysis with Deep Bi-GRU-CRF Network , 2018, ArXiv.

[11]  Jing Xiao,et al.  Unidirectional Memory-Self-Attention Transducer for Online Speech Recognition , 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[12]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[13]  Rico Sennrich,et al.  Improving Neural Machine Translation Models with Monolingual Data , 2015, ACL.

[14]  Hao Zheng,et al.  AISHELL-1: An open-source Mandarin speech corpus and a speech recognition baseline , 2017, 2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA).