DeepAI AI Chat
Log In Sign Up

Towards Unsupervised Speech-to-Text Translation

by   Yu-An Chung, et al.

We present a framework for building speech-to-text translation (ST) systems using only monolingual speech and text corpora, in other words, speech utterances from a source language and independent text from a target language. As opposed to traditional cascaded systems and end-to-end architectures, our system does not require any labeled data (i.e., transcribed source audio or parallel source and target text corpora) during training, making it especially applicable to language pairs with very few or even zero bilingual resources. The framework initializes the ST system with a cross-modal bilingual dictionary inferred from the monolingual corpora, that maps every source speech segment corresponding to a spoken word to its target text translation. For unseen source speech utterances, the system first performs word-by-word translation on each speech segment in the utterance. The translation is improved by leveraging a language model and a sequence denoising autoencoder to provide prior knowledge about the target language. Experimental results show that our unsupervised system achieves comparable BLEU scores to supervised end-to-end models despite the lack of supervision. We also provide an ablation analysis to examine the utility of each component in our system.


page 1

page 2

page 3

page 4


Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation

This paper proposes a first attempt to build an end-to-end speech-to-tex...

Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces

Recent research has shown that word embedding spaces learned from text c...

Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation

Direct speech-to-speech translation (S2ST) is an attractive research top...

Unsupervised Neural Text Simplification

The paper presents a first attempt towards unsupervised neural text simp...

End-to-end Speech Translation via Cross-modal Progressive Training

End-to-end speech translation models have become a new trend in the rese...

Unsupervised Word Segmentation using K Nearest Neighbors

In this paper, we propose an unsupervised kNN-based approach for word se...

Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech

Polyphone disambiguation aims to capture accurate pronunciation knowledg...