top of page
AI-WOW_logo-01.png

Motion-graphics

Principle

Application

Deep Learning
Model RNN
Word Embedding
Sentence Generation
語音辨識_infographic_英文版_OL-01.jpg
Extended Reading
Semantic Understanding
NLP
Voice Recognition
Speech Synthesis
Vector

Extended Reading :

1.【深度學習】如果電腦有神經,可以教它做什麼?
https://reurl.cc/YlOb60

2. 遞歸神經網路(RNN)和長短期記憶模型(LSTM)的運作原理

https://reurl.cc/6gaMlb

 

 

3. 詞向量介紹

https://pse.is/L3JD5

4. 教電腦畫畫:初心者的生成式對抗網路(GAN)入門筆記

https://pse.is/JUXCQ

 

5. How to Keep Your Smart Assistant Voice Recordings Private

https://is.gd/7Cdyq7

Advanced Reading :

Advanced Reading

1. 基於深度學習之語音增強技術 /曹昱、王緒翔 (2019) IEEE

Time-Domain Multi-modal Bone/air Conducted Speech Enhancement/Syu-Siang Wang, Yu Tsao (2019) IEEE

https://reurl.cc/ZOp50p

2. Recurrent Neural Network Based Language Model Personalization by Social Network Crowdsourcing

Hung-yi Lee (2013) INTERSPEECH

https://reurl.cc/Y1yryL

3. Experimental Study on Extreme Learning Machine Applications for Speech Enhancement / Chi-Chun Lee (2017) IEEE

https://reurl.cc/Mddepk

 

Info-graphics

Principle

Application

bottom of page