Speech-to-speech Translation between Untranscribed Unknown Languages
arXiv:1910.00795
Abstract
In this paper, we explore a method for training speech-to-speech translation tasks without any transcription or linguistic supervision. Our proposed method consists of two steps: First, we train and generate discrete representation with unsupervised term discovery with a discrete quantized autoencoder. Second, we train a sequence-to-sequence model that directly maps the source language speech to the target language's discrete representation. Our proposed method can directly generate target speech without any auxiliary or pre-training steps with a source or target transcription. To the best of our knowledge, this is the first work that performed pure speech-to-speech translation between untranscribed unknown languages.
arXiv commentAccepted in IEEE ASRU 2019. Web-page for more samples & details: https://sp2code-translation-v1.netlify.com/
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Neural Discrete Representation Learning
- Empirical Evaluation of Rectified Activations in Convolutional Network
- Attention-Based Models for Speech Recognition
- Fast Decoding in Sequence Models using Discrete Latent Variables
- Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation
- Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion
- Direct speech-to-speech translation with a sequence-to-sequence model