2021/06/01 by Xingshan Zeng, Zeng, Xingshan, Liangyou Li +2
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Natural Language Processing Techniques #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2106.00197
openalex publication_date 2021/06/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper describes the system submitted to the IWSLT 2021 Multilingual Speech Translation (MultiST) task from Huawei Noah's Ark Lab. We use a unified transformer architecture for our MultiST model, so that the data from different modalities (i.e., speech and text) and different tasks (i.e., Speech Recognition, Machine Translation, and Speech Translation) can be exploited to enhance the model's ability. Specifically, speech and text inputs are firstly fed to different feature extractors to extract acoustic and textual features, respectively. Then, these features are processed by a shared encoder--decoder architecture. We apply several training techniques to improve the performance, including multi-task learning, task-level curriculum learning, data augmentation, etc. Our final system achieves significantly better results than bilingual baselines on supervised language pairs and yields reasonable results on zero-shot language pairs.