Skills

What am I (supposed to be) good at?

Speech Recognition

Experience with CMU Sphinx, Kaldi, HTK, Julius and DeepSpeech for Brazilian Portuguese

Speech Synthesis

HTS, Klatt

Embedded Hardware

Raspberry Pi, Beaglebone Black and NTC C.H.I.P. SBCs; and the Arduino platform

Assistive Technology

Software- and hardware-based solutions for people with visual, hearing and upper-limb motor disabilities

Genetic Algorithms

Applications for the routing and wavelength assignment (RWA) problem in wavelength-multiplexed (WDM) optical networks

Linux

Debian, Arch, Vim, Git, Yakuake, Bash, Python, C, LaTeX, MATLAB (is that enough?)

Experience

 
 
 
 
 
December 2017 – December 2021
Belém, Brazil

PhD in Computer Science

Federal University of Pará (UFPA)

Speech-based technologies:

  • Kaldi ASR for Brazilian Portuguese
  • Utterance copy TTS in English using Klatt and deep learning techniques
 
 
 
 
 
March 2017 – December 2017
Belém, Brazil

MSc in Computer Science

Federal University of Pará (UFPA)

A universal remote control system in C++ for people with upper-limb motor disabilities, so they could control a TV via alternative methods.

  • OpenCV for head gesture recognition
  • PocketSphinx for speech recognition
  • Adaptive switches in hardware
 
 
 
 
 
March 2016 – December 2016
Belém, Brazil

Research Internship

Embrapa

A simulator in Python for the routing and wavelength assignment (RWA) problem over transparent, wavelength-multiplexed optical networks using Genetic Algorithms.
 
 
 
 
 
March 2014 – January 2015
Budapest, Hungary

Summer Internship

Óbuda University (OE)

Development of speech (English) modules for controlling Teki: a personal home assistant, Turtlebot-based robot

  • PocketSphinx desktop on Linux + ROS (offline)
  • Android’s Google ASR (online Wi-Fi UDP connection)
 
 
 
 
 
January 2012 – February 2016
Belém, Brazil

Research Internship

Federal University of Pará (UFPA)

Development of resources and applications for spech recognition in Brazilian Portuguese:

  • PyQt4 CFG/BNF grammar tester for Julius
  • Acoustic model training on CMU Sphinx for KDE Simon Listens
  • Android client + Julius server vs. Google’s Android ASR

Recent Posts

Projects

ASR Remote

A low cost, open-source, universal-like remote control system that translates the user’s spoken words into commands to electronic devices

Recent Publications

Quickly discover relevant content by filtering publications.

Statistical comparison among three different types of mouse click: mouth puffing, EMG and dwell-time. Two out of these three methods …

Estimating the input parameter of Klatt88 formant-based speech synthesizer with long short-term memory neural nets (LSTM).

The first attempt to create scripts and baseline acoustic models for Brazilian Portuguese using Kaldi tools.

A genetic algorithm for solving the RWA problem, which consists of choosing the most suitable lightpath (i.e., a combination of a route …

GCSplit: an open-source, bioinformatic tool which partitions metagenomic sequences into subsets using a computationally inexpensive …

Contact