Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling (2019-02-21T00:00:00.000000Z)

TL;DR

This document outlines the underlying design of Lingvo and serves as an introduction to the various pieces of the framework, while also offering examples of advanced features that showcase the capabilities of the Framework.

Abstract

Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models. Lingvo models are composed of modular building blocks that are flexible and easily extensible, and experiment configurations are centralized and highly customizable. Distributed training and quantized inference are supported directly within the framework, and it contains existing implementations of a large number of utilities, helper functions, and the newest research ideas. Lingvo has been used in collaboration by dozens of researchers in more than 20 papers over the last two years. This document outlines the underlying design of Lingvo and serves as an introduction to the various pieces of the framework, while also offering examples of advanced features that showcase the capabilities of the framework.

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

TL;DR

Abstract

Authors

References24 items

Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation

Hierarchical Generative Modeling for Controllable Speech Synthesis

Compression of End-to-End Models

Contextual Speech Recognition in End-to-end Neural Network Systems Using Beam Search

Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation

Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions

Monotonic Chunkwise Attention

An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model

Multi-Dialect Speech Recognition with a Single Sequence-to-Sequence Model

Improving the Performance of Online Neural Transducer Models

Minimum Word Error Rate Training for Attention-Based Sequence-to-Sequence Models

No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models

State-of-the-Art Speech Recognition with Sequence-to-Sequence Models

Speech recognition for medical conversations

Learning Hard Alignments with Variational Inference

Sequence-to-Sequence Models Can Directly Translate Foreign Speech

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

Neural Machine Translation of Rare Words with Subword Units

Japanese and Korean voice search

Et al

End-to-End Multilingual Speech Recognition using Encoder-Decoder Models

Introduction to Lingvo

and as an in