This page aims to promote the Mr. Falante, which is a personal project about speech processing in Brazilian Portuguese. This project aims to research, develop and train models based on Deep Learning (DL) for speech processing. Among these projects, models for speech synthesis (Text-to-Speech - TTS), speech transcription (Speech-to-Text - STT), speaker recognition, Speaker Diarization, Denoisers, Upsampling, etc.

Artificial Intelligence (AI) can be seen as the ability of a machine to reproduce human-like skills. It involves developing systems that can learn autonomously, recognizing patterns and generating insights without being explicitly programmed to do so. Unlike traditional programming, AI-based models learn to extract patterns from examples, i.e. data. DL-based models need a lot of data, learning from experience, and thus being able to perform tasks like us humans.