HW-TSC at IWSLT2023: Break the Quality Ceiling of Offline Track via Pre-Training and Domain Adaptation

Abstract

This paper describes HW-TSC’s submissions to the IWSLT 2023 Offline Speech Translation task, including speech translation of talks from English to German, English to Chinese and English to Japanese. We participated in all three tracks (Constrained training, Constrained with Large Language Models training, Unconstrained training), with using cascaded architectures models. We use data enhancement, pretraining models and other means to improve the quality of ASR, and use a variety of techniques including R-Drop, deep model, domain data selection, etc. to improve the quality of NMT. Compared with last year’s best results, we have improved by 2.1 BLEU in the MuST-C English-German test set.