Skip to content
conftrace_
2022 ACL ACL 2022

NAIST Simultaneous Speech-to-Text Translation System for IWSLT 2022

Abstract

AbstractThis paper describes NAIST’s simultaneous speech translation systems developed for IWSLT 2022 Evaluation Campaign. We participated the speech-to-speech track for English-to-German and English-to-Japanese. Our primary submissions were end-to-end systems using adaptive segmentation policies based on Prefix Alignment.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Speech & Audio
🐣 Hot Topic Early Bird - speech-to-speech translation

Authors

Ryo Fukuda, Yuka Ko, Yasumasa Kano, Kosuke Doi, Hirotaka Tokuyama, Sakriani Sakti, Katsuhito Sudoh, Satoshi Nakamura

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Application Areas > Efficient Computing Deep Learning > Learning Types > Transfer Learning Speech & Audio > Recognition > Speech Translation

Keywords

adaptive segmentation speech-to-speech translation speech translation simultaneous translation end-to-end system prefix alignment
Download PDF

More from ACL 2022

All ACL 2022 papers →
MLLP-VRAIN UPV systems for the IWSLT 2022 Simultaneous Speech Translation and Speech-to-Speech Translation tasks
Pretrained Speech Encoders and Efficient Fine-tuning Methods for Speech Translation: UPC at IWSLT 2022
CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022
The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation
CMU’s IWSLT 2022 Dialect Speech Translation System
ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks