SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.08709 · ACL · 2023

Back Translation for Speech-to-text Translation Without Transcripts

Code, Yang Feng, Qingkai Fang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The success of end-to-end speech-to-text translation (ST) is often achieved by utilizing source transcripts, e.g., by pre-training with automatic speech recognition (ASR) and machine translation (MT) tasks, or by introducing additional ASR and MT data. Unfortunately, transcripts are only sometimes available since numerous unwritten languages exist worldwide. In this paper, we aim to utilize large amounts of targetside monolingual data to enhance ST without transcripts. Motivated by the remarkable success of back translation in MT, we develop a back translation algorithm for ST (BT4ST) to synthesize pseudo ST data from monolingual target data. To ease the challenges posed by short-to-long generation and one-to-many mapping, we introduce self-supervised discrete units and achieve back translation by cascading a target-to-unit model and a unit-to-speech model. With our synthetic ST data, we achieve an average boost of 2.3 BLEU on MuST-C En→De, En→Fr, and En→Es datasets. More experiments show that our method is especially effective in low-resource scenarios. 12

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.08709")
get_code_for_paper("2305.08709")
have("2305.08709")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.08709.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.08709.svg)](https://syntology.ai/paper/2305.08709)

Connect an agent — have() is free.