Português / English
Hi!

My name is Felipe and I am a 🇧🇷 engineer/researcher with more than 10 years of experience in AI, speech signal processing and digital image processing.

Among my latest obssesions, I can list:
Applications of AI in audio, such as Automatic Speech Recognition, Speaker Identification and Diarization (here you can find a tiny speaker recognition model (less than 10MB) that achieves >95% accuracy in a dataset with 100 different people).
Speech enhancement and improvement of quality and intelligibility (including here you can find BAM, the speech enhancement technique I developed during my Ph.D. studies, the journal paper I published about it, in case you want to know how I did it, and my thesis in case you want the extended version).
• Development of web applications (I'm still starting here, but I wrote this website you see. Look at the source code).
You may check out my Github to see what I work on in my free time, my Google Scholar with my publications and my Spotify with the music I make when I'm not at the computer :)