Direct Speech-to-Speech Translation With Discrete Units

By Ann Lee, Peng-Jen Chen, Changhan Wang, Jiatao Gu, Xutai Ma, Adam Polyak, Yossi Adi, Qing He, Yun Tang, Juan Pino and 1 more. 2021

241 citations recorded by the source corpus.

We present a direct speech-to-speech translation (S2ST) model that translates speech from one language to speech in another language without relying on intermediate text generation. We tackle the problem by first applying a self-supervised discrete speech encoder on the target speech and then training a sequence-to-sequence speech-to-unit translation (S2UT) model to predict the discrete representations of the target speech. When target text transcripts are available, we design a joint speech and text training framework that enables the model to generate dual modality output (speech and text) simultaneously in the same inference pass. Experiments on the Fisher Spanish-English dataset show that the proposed framework yields improvement of 6.7 BLEU compared with a baseline direct S2ST model that predicts spectrogram features. When trained without any text transcripts, our model performance is comparable to models that predict spectrograms and are trained with text supervision, showing the potential of our system for translation between unwritten languages.

Subfields: Artificial Intelligence, Machine Translation, Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Wei-Ning Hsu
  2. Yossi Adi
  3. Furu Wei
  4. Jinyu Li
  5. Gabriel Synnaeve
  6. Mohit Bansal
  7. Yoshua Bengio
  8. Jianfeng Gao

In Machine Translation

  1. Juan Pino
  2. Changhan Wang
  3. Ye Jia
  4. Yossi Adi
  5. Yun Tang
  6. Xutai Ma
  7. Ann Lee
  8. Michelle Tadmor Ramanovich

In Speech & Audio

  1. Wei-Ning Hsu
  2. Yossi Adi
  3. Jinyu Li
  4. Gabriel Synnaeve
  5. Jade Copet
  6. Shinji Watanabe
  7. Abdel-rahman Mohamed
  8. Ann Lee

Citations in the corpus