Speech Machine Learning Researcher
San Mateo, California, United States
patrickltobing@gmail.com
Skills
Voice Conversion and Speech Synthesis
Machine Learning and Neural Network
Python/PyTorch/TorchScript/JIT
C/C++/Intel AVX
Languages
Indonesian
English
Japanese
Links
AI/ML for Speech Synthesis and Processing
Project: End-to-End Speech Synthesis and Voice Conversion with Human-Level Performance and Quality on Highly Expressive Multilingual Noisy Real-World Data
Project: Low-Latency Real-Time High-Quality Voice Conversion with Neural Vocoder Trained on Non-Parallel Multispeaker and Multilingual Data
Project: Automatic Detection of Risky Driving Scenes with Variational Autoencoder and Clustering Technique on Multimodal Driving Data
Project: Development of Voice Conversion and Neural Vocoder Techniques
Project: Latent Trajectory Modeling for Acoustic-Articulatory Mapping
Project: High-School Curriculum Education Web System
Project: Speech Modification with Acoustic-Articulatory Mapping based on Gaussian Mixture Model
Ph.D. Degree in Information Science
Thesis: High-Quality and Flexible Voice Conversion Techniques based on Statistical Spectral and Waveform Modeling [PDF]
Master's Degree in Information Science
Thesis: Articulatory Controllable Speech Modification using Statistical Feature Mapping Techniques [PDF]
Bachelor's Degree in Informatics Engineering
Thesis: Indonesian Text-to-Speech System based on Hidden Markov Model [PDF (Indonesian)]
Topic: Silent Speech Enhancement in Noisy Environments with Air- and Body-Conducted Speech Processing
Presentation Title: Articulatory controllable speech modification based on Gaussian mixture models with direct waveform modification using spectrum differential
Scholarship and Full Tuition Fee Exemption during Master’s Course in NAIST, Japan