Speech-to-speech translation

Authors: Ye Jia *, Ron J. Weiss *, Fadi Biadsy, Wolfgang Macherey, Melvin Johnson, Zhifeng Chen, Yonghui Wu. Abstract: We present an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation. The network is trained end-to-end, learning to map speech spectrograms into target spectrograms in another language, corresponding to the translated content (in a differe

3 mentions: @katsuhitosudoh@buyouyuhao@iandanforth
Date: 2019/04/15 23:16

Referring Tweets

@katsuhitosudoh 音声はココ.けっこうまともに音出てるような気がする(個人の感想です) t.co/bAn1Ll4S6A Translatotronって名前はちょっと発音しづらいぜ...
@buyouyuhao Believe it or not, Google can now directly translating from speech to speech, without transcribing to text first. t.co/XwOdIZtVu1
@iandanforth Audio samples don't work yet for me, but presumably will in the near future - t.co/hCsj8YdNYY

Related Entries

Read more Adaptation Data Selection using Neural Language Models: Experiments in Machine Translation - ACL Ant...
0 users, 1 mentions 2019/10/01 14:18
Read more Reading: An Effective Approach to Unsupervised Machine Translation (Artetxe et al. ACL 2019) - Speak...
0 users, 1 mentions 2019/12/07 05:20
Read more Mask-Predict: Parallel Decoding of Conditional Masked Language Models - ACL Anthology
0 users, 1 mentions 2020/01/17 03:51
Read more [2001.02366] What can robotics research learn from computer vision research?contact arXivarXiv Twitt...
0 users, 2 mentions 2020/01/20 20:20
Read more Quality Estimation Task - EMNLP fifth Conference on Machine Translation
0 users, 1 mentions 2020/03/19 23:20