JC Ulundo
Kaomiru (XWARE 2019) – AI/ML Engineer
This was an application that we designed to conduct automatic web interviews using Speech to Text, image recognition, and audio speech pattern study, text summarization and sentiment analysis. My contribution for this project was to elaborate and build the speech to text part to collect the data for our text dataset, analyze the text and present the key elements from the speech to a more summarized format. For this I used: ● Google cloud STT API; ● IBM Watson; ● LSTMs; Programing Languages: Python, JSON, SQLite;