Share This Author
TensorFlow: A system for large-scale machine learning
- Martín Abadi, P. Barham, Xiaoqiang Zhang
- Computer ScienceUSENIX Symposium on Operating Systems Design and…
- 27 May 2016
The TensorFlow dataflow model is described and the compelling performance that Tensor Flow achieves for several real-world applications is demonstrated.
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
The TensorFlow interface and an implementation of that interface that is built at Google are described, which has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields.
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
GNMT, Google's Neural Machine Translation system, is presented, which attempts to address many of the weaknesses of conventional phrase-based translation systems and provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delicited models.
Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions
- Jonathan Shen, Ruoming Pang, Yonghui Wu
- Computer ScienceIEEE International Conference on Acoustics…
- 16 December 2017
This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps…
Tacotron: Towards End-to-End Speech Synthesis
Tacotron is presented, an end-to-end generative text- to-speech model that synthesizes speech directly from characters that achieves a 3.82 subjective 5-scale mean opinion score on US English, outperforming a production parametric system in terms of naturalness.
Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
- Melvin Johnson, M. Schuster, J. Dean
- Computer ScienceInternational Conference on Topology, Algebra and…
- 14 November 2016
This work proposes a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages using a shared wordpiece vocabulary, and introduces an artificial token at the beginning of the input sentence to specify the required target language.
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
- Yanping Huang, Yonglong Cheng, Z. Chen
- Computer ScienceNeural Information Processing Systems
- 16 November 2018
GPipe is introduced, a pipeline parallelism library that allows scaling any network that can be expressed as a sequence of layers by pipelining different sub-sequences of layers on separate accelerators, resulting in almost linear speedup when a model is partitioned across multiple accelerators.
LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
Experimental results show that neural end-to-end TTS models trained from the LibriTTS corpus achieved above 4.0 in mean opinion scores in naturalness in five out of six evaluation speakers.
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
It is shown that randomly sampled speaker embeddings can be used to synthesize speech in the voice of novel speakers dissimilar from those used in training, indicating that the model has learned a high quality speaker representation.
GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
- Dmitry Lepikhin, HyoukJoong Lee, Z. Chen
- Computer ScienceInternational Conference on Learning…
- 30 June 2020
GShard enabled us to scale up multilingual neural machine translation Transformer model with Sparsely-Gated Mixture-of-Experts beyond 600 billion parameters using automatic sharding and it is demonstrated that such a giant model can efficiently be trained on 2048 TPU v3 accelerators in 4 days to achieve far superior quality for translation from 100 languages to English compared to the prior art.