Аннотация
We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks. Deep Voice lays the groundwork for truly end-to-end neural speech synthesis. The system comprises five major building blocks: a segmentation model for locating phoneme boundaries, a grapheme-to-phoneme conversion model, a phoneme duration prediction model, a fundamental frequency prediction model, and an audio synthesis model.
For the segmentation model, we propose a novel way of performing phoneme boundary detection with deep neural networks using connectionist temporal classif i cation (CTC) loss. For the audio synthesis model, we implement a variant of WaveNet that requires fewer parameters and trains faster than the original. By using a neural network for each component, our system is simpler and more f l exible than traditional text-to-speech systems, where each component requires laborious feature engineering and extensive domain expertise. Finally, we show that inference with our system can be performed faster than real time and describe optimized WaveNet inference kernels on both CPU and GPU that achieve up to 400x speedups over existing implementations.
![Automate the Boring Stuff with Python [Practical Programming for Total Beginners]](https://www.rulit.me/data/programs/images/automate-the-boring-stuff-with-python-practical-programming_570900.jpg "If you’ve ever spent hours renaming files or updating hundreds of spreadsheet cells, you know how tedious tasks like these can be. But what if you could have your computer do them for you?
In Automate the Boring Stuff with Python, you’ll learn how to use Python to write programs that do in...")
Комментарии к книге "Deep Voice: Real-time Neural Text-to-Speech"