Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation

Résumé

Boosted by the simultaneous translation shared task at IWSLT 2020, promising end-to-end online speech translation approaches were recently proposed. They consist in incrementally encoding a speech input (in a source language) and decoding the corresponding text (in a target language) with the best possible trade-off between latency and translation quality. This paper investigates two key aspects of end-to-end simultaneous speech translation: (a) how to encode efficiently the continuous speech flow, and (b) how to segment the speech flow in order to alternate optimally between reading (R: encoding input) and writing (W: decoding output) operations. We extend our previously proposed end-to-end online decoding strategy and show that while replacing BLSTM by ULSTM encoding degrades performance in offline mode, it actually improves both efficiency and performance in online mode. We also measure the impact of different methods to segment the speech signal (using fixed interval boundaries, oracle word boundaries or randomly set boundaries) and show that our best end-to-end online decoding strategy is surprisingly the one that alternates R/W operations on fixed size blocks on our English-German speech translation setup.
Fichier principal
Vignette du fichier
2104.14470.pdf (259.38 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03372487 , version 1 (10-10-2021)

Identifiants

  • HAL Id : hal-03372487 , version 1

Citer

Ha Nguyen, Yannick Estève, Laurent Besacier. Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation. INTERSPEECH 2021, Aug 2021, Brno, Czech Republic. ⟨hal-03372487⟩
58 Consultations
91 Téléchargements

Partager

Gmail Facebook X LinkedIn More