End to End Speech Translation
Related Papers
Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018
AbstractThis paper describes FBK’s submission to the end-to-end English-German speech translation task at IWSLT 2018. Our system relies on a state-of-the-art model based on LSTMs and CNNs, where the CNNs …...
Data Augmentation for End-to-End Speech Translation: FBK@IWSLT ‘19
AbstractThis paper describes FBK’s submission to the end-to-end speech translation (ST) task at IWSLT 2019. The task consists in the “direct” translation (i.e. without intermediate discrete representation) of English speech …...
End-to-end Speech Translation System Description of LIT for IWSLT 2019
AbstractThis paper describes our end-to-end speech translation system for the speech translation task of lectures and TED talks from English to German for IWSLT Evaluation 2019. We propose layer-tied self-attention …...
Curriculum Pre-training for End-to-End Speech Translation
AbstractEnd-to-end speech translation poses a heavy burden on the encoder because it has to transcribe, understand, and learn cross-lingual semantics simultaneously. To obtain a powerful encoder, traditional methods pre-train it …...
Beyond Sentence-Level End-to-End Speech Translation: Context Helps
AbstractDocument-level contextual information has shown benefits to text-based machine translation, but whether and how context helps end-to-end (E2E) speech translation (ST) is still under-studied. We fill this gap through extensive …...
Learning Shared Semantic Space for Speech-to-Text Translation
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 …...
Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation
AbstractEnd-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. However, the training of end-to-end methods relies on parallel ST …...
Non-Parametric Domain Adaptation for End-to-End Speech Translation
AbstractThe end-to-end speech translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency and fewer parameters. However, the effectiveness of neural-based approaches to …...
CTC-based Non-autoregressive Speech Translation
AbstractCombining end-to-end speech translation (ST) and non-autoregressive (NAR) generation is promising in language and speech processing for their advantages of less error propagation and low latency. In this paper, we …...
Generating Synthetic Speech from SpokenVocab for Speech Translation
AbstractTraining end-to-end speech translation (ST) systems requires sufficiently large-scale data, which is unavailable for most language pairs and domains. One practical solution to the data scarcity issue is to convert …...
Understanding and Bridging the Modality Gap for Speech Translation
AbstractHow to achieve better end-to-end speech translation (ST) by leveraging (text) machine translation (MT) data? Among various existing techniques, multi-task learning is one of the effective ways to share knowledge …...