Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Hands-On Natural Language Processing with Python

You're reading from   Hands-On Natural Language Processing with Python A practical guide to applying deep learning architectures to your NLP applications

Arrow left icon
Product type Paperback
Published in Jul 2018
Publisher Packt
ISBN-13 9781789139495
Length 312 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Authors (5):
Arrow left icon
Rajalingappaa Shanmugamani Rajalingappaa Shanmugamani
Author Profile Icon Rajalingappaa Shanmugamani
Rajalingappaa Shanmugamani
Chaitanya Joshi Chaitanya Joshi
Author Profile Icon Chaitanya Joshi
Chaitanya Joshi
Auguste Byiringiro Auguste Byiringiro
Author Profile Icon Auguste Byiringiro
Auguste Byiringiro
Rajesh Arumugam Rajesh Arumugam
Author Profile Icon Rajesh Arumugam
Rajesh Arumugam
Karthik Muthuswamy Karthik Muthuswamy
Author Profile Icon Karthik Muthuswamy
Karthik Muthuswamy
+1 more Show less
Arrow right icon
View More author details
Toc

Table of Contents (15) Chapters Close

Preface 1. Getting Started 2. Text Classification and POS Tagging Using NLTK FREE CHAPTER 3. Deep Learning and TensorFlow 4. Semantic Embedding Using Shallow Models 5. Text Classification Using LSTM 6. Searching and DeDuplicating Using CNNs 7. Named Entity Recognition Using Character LSTM 8. Text Generation and Summarization Using GRUs 9. Question-Answering and Chatbots Using Memory Networks 10. Machine Translation Using the Attention-Based Model 11. Speech Recognition Using DeepSpeech 12. Text-to-Speech Using Tacotron 13. Deploying Trained Models 14. Other Books You May Enjoy

TTS in deep learning

Over the last few years, the field of TTS has been shaken by several deep learning-based breakthroughs. Here, we will present two of them: WaveNet (probably the most notorious one) and Tacotron (which has the advantage of being an end-to-end approach).

WaveNet, in brief

The WaveNet paper was presented in 2016, and it showed results that outperformed the classical TTS approaches. Basically, WaveNet is an audio generative model. It takes a sequence of audio samples as input and predicts the most likely following audio sample. By adding an extra input, it can be conditioned to accomplish more tasks. For instance, if the audio transcript is additionally provided during training, WaveNet can turn it into a...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at €18.99/month. Cancel anytime