Skip to search formSkip to main contentSkip to account menu

TensorFlow: A system for large-scale machine learning

The TensorFlow dataflow model is described and the compelling performance that TensorFlow achieves for several real-world applications is demonstrated.
arXiv (opens in a new tab)

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.
arXiv (opens in a new tab)

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.
arXiv (opens in a new tab)

Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions

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…
IEEE (opens in a new tab)

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.
arXiv (opens in a new tab)

Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

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.
ACL (opens in a new tab)

GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism

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.
View Paper (opens in a new tab)

GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding

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.
arXiv (opens in a new tab)

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.
arXiv (opens in a new tab)

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.
arXiv (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)
  NODES
Association 1
INTERN 2
Note 1