Textless Speech-to-Speech Translation on Real Data

by   Ann Lee, et al.

We present a textless speech-to-speech translation (S2ST) system that can translate speech from one language into another language and can be built without the need of any text data. Different from existing work in the literature, we tackle the challenge in modeling multi-speaker target speech and train the systems with real-world S2ST data. The key to our approach is a self-supervised unit-based speech normalization technique, which finetunes a pre-trained speech encoder with paired audios from multiple speakers and a single reference speaker to reduce the variations due to accents, while preserving the lexical content. With only 10 minutes of paired data for speech normalization, we obtain on average 3.2 BLEU gain when training the S2ST model on the  S2ST dataset, compared to a baseline trained on un-normalized speech target. We also incorporate automatically mined S2ST data and show an additional 2.0 BLEU gain. To our knowledge, we are the first to establish a textless S2ST technique that can be trained with real-world data and works for multiple language pairs.


page 1

page 2

page 3

page 4


Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain suc...

Direct speech-to-speech translation with discrete units

We present a direct speech-to-speech translation (S2ST) model that trans...

Large-Scale Self- and Semi-Supervised Learning for Speech Translation

In this paper, we improve speech translation (ST) through effectively le...

Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training

Simultaneous speech-to-speech translation is widely useful but extremely...

Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation

Direct speech-to-speech translation (S2ST) models suffer from data scarc...

CycleGAN-Based Unpaired Speech Dereverberation

Typically, neural network-based speech dereverberation models are traine...

Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation

End-to-end speech-to-speech translation (S2ST) without relying on interm...