Learning Shared Semantic Space for Speech-to-Text Translation
Authors:
Preprint
Abstract
Having numerous potential applications and great impact, end-to-end speech translation (ST) has long been treated as an independent task, failing to fully draw strength from the rapid advances of its sibling - text machine translation (MT). With text and audio inputs represented differently, the modality gap has rendered MT data and its end-to-end models incompatible with their ST counterparts. In observation of this obstacle, we propose to bridge this representation gap with Chimera. By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and boosts the performance on ST benchmarks, MuST-C and Augmented Librispeech, to a new state-of-the-art. Specifically, Chimera obtains 27.1 BLEU on MuST-C EN-DE, improving the SOTA by a +1.9 BLEU margin. Further experimental analyses demonstrate that the shared semantic space indeed conveys common knowledge between these two tasks and thus paves a new way for augmenting training resources across modalities. Code, data, and resources are available at https://github.com/Glaciohound/Chimera-ST.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation2020
- Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation2020
- ESPnet-ST: All-in-One Speech Translation Toolkit2020
- Curriculum Pre-training for End-to-End Speech Translation2020
- Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation2019
- Towards Fluent Translations From Disfluent Speech2018
- End-to-End Automatic Speech Translation of Audiobooks2018
- Reading Differences and Brain: Cortical Integration of Speech and Print in Sentence Processing Varies With Reader SkillDevelopmental Neuropsychology, 2008
- Converging Language Streams in the Human Temporal LobeJournal of Neuroscience, 2006
- Integration of Letters and Speech Sounds in the Human BrainNeuron, 2004