Without Further Ado: Direct and Simultaneous Speech Translation by AppTek in 2021
Parnia Bahar, Patrick Wilken, Mattia Antonino Di Gangi, Evgeny Matusov · 2021
This paper describes the offline and simultaneous speech translation (ST) systems developed at AppTek for IWSLT 2021.Our offline ST submission includes the direct endto-end system and the so-called posterior tight integrated model, which is akin to the cascade system but is trained in an end-to-end fashion, where all the cascaded modules are end-to-end models themselves.For simultaneous ST, we combine hybrid automatic speech recognition (ASR) with a machine translation (MT) approach whose translation policy decisions are learned from statistical word alignments.Compared to last year, we improve general quality and provide a wider range of quality/latency trade-offs, both due to a data augmentation method making the MT model robust to varying chunk sizes.Finally, we present a method for ASR output segmentation into sentences that introduces a minimal additional delay.