Automatic Song Translation for Tonal Languages

03/25/2022
by   Fenfei Guo, et al.
0

This paper develops automatic song translation (AST) for tonal languages and addresses the unique challenge of aligning words' tones with melody of a song in addition to conveying the original meaning. We propose three criteria for effective AST – preserving meaning, singability and intelligibility – and design metrics for these criteria. We develop a new benchmark for English–Mandarin song translation and develop an unsupervised AST system, Guided AliGnment for Automatic Song Translation (GagaST), which combines pre-training with three decoding constraints. Both automatic and human evaluations show GagaST successfully balances semantics and singability.

READ FULL TEXT
research
11/20/2008

chi2TeX Semi-automatic translation from chiwriter to LaTeX

Semi-automatic translation of math-filled book from obsolete ChiWriter f...
research
10/26/2021

Assessing Evaluation Metrics for Speech-to-Speech Translation

Speech-to-speech translation combines machine translation with speech sy...
research
04/05/2020

Machine Translation Pre-training for Data-to-Text Generation – A Case Study in Czech

While there is a large body of research studying deep learning methods f...
research
12/29/2020

The Parallel Meaning Bank: A Framework for Semantically Annotating Multiple Languages

This paper gives a general description of the ideas behind the Parallel ...
research
06/06/2019

Unsupervised Pivot Translation for Distant Languages

Unsupervised neural machine translation (NMT) has attracted a lot of att...
research
08/13/2018

Automatic Reference-Based Evaluation of Pronoun Translation Misses the Point

We compare the performance of the APT and AutoPRF metrics for pronoun tr...
research
12/07/2020

What Meaning-Form Correlation Has to Compose With

Compositionality is a widely discussed property of natural languages, al...

Please sign up or login with your details

Forgot password? Click here to reset