from Machine Learning Engineer at Warung Pintar
A machine learning engineer focuses in speech domain, building end-to-end speech recognition system using deep learning.
"In this talk, I will present a broader view about speech recognition and deep learning, from research papers, applications, and challenges"
I am a machine learning engineer that focuses on develop and implement speech recognition technology for everyone. I am a writer and editor of medium publication namely Data Folks Indonesia, writing about machine learning, deep learning, and its applications. I use Python for everything, literally everything, from scraping, modeling, and visualizing. I love to learn, write and talk about data science, machine learning, and deep learning
Automatic Speech Recognition aims to enable natural human-machine interaction, has been an intensive research area for decades. Imagine, you are a seller in an Indonesian traditional market where you sell raw meat and you must collect the transaction, and it is usually done by a cash register. A typical seller does not have a budget or aware to buy or use such kind of machine. Therefore, you need an inexpensive machine and take you easy to collect a transaction.
There is also a recent trend that the power of deep learning is not only used to classify images or translated a document from one language to another. In a few decades ago, a lot of researchers are trying to utilize deep learning to translate from speech to text. To develop that kind of model, python is a good environment to start, there are a lot of libraries to support the process and experiment done by researchers that use a python to implement their papers.