DeepAI
Log In Sign Up

Simultaneous Speech-to-Speech Translation System with Neural Incremental ASR, MT, and TTS

11/10/2020
by   Katsuhito Sudoh, et al.
0

This paper presents a newly developed, simultaneous neural speech-to-speech translation system and its evaluation. The system consists of three fully-incremental neural processing modules for automatic speech recognition (ASR), machine translation (MT), and text-to-speech synthesis (TTS). We investigated its overall latency in the system's Ear-Voice Span and speaking latency along with module-level performance.

READ FULL TEXT
05/24/2020

ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020

This paper describes the ON-TRAC Consortium translation systems develope...
10/15/2021

Incremental Speech Synthesis For Speech-To-Speech Translation

In a speech-to-speech translation (S2ST) pipeline, the text-to-speech (T...
03/22/2020

Low Latency ASR for Simultaneous Speech Translation

User studies have shown that reducing the latency of our simultaneous le...
06/10/2018

Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation

We address the problem of simultaneous translation by modifying the Neur...
07/30/2019

DuTongChuan: Context-aware Translation Model for Simultaneous Interpreting

In this paper, we present DuTongChuan, a novel context-aware translation...
11/23/2021

Romanian Speech Recognition Experiments from the ROBIN Project

One of the fundamental functionalities for accepting a socially assistiv...
12/09/2020

On Knowledge Distillation for Direct Speech Translation

Direct speech translation (ST) has shown to be a complex task requiring ...