HCT banner image

Brain2Speech

HCT Lab + ISRL Lab

Realizing state-of-the-art brain computer interfaces and 3D biomechanical articulatory speech synthesis.

People

Sid Fels
Sid Fels
Professor, Director (HCT Lab)

Bryan Gick
Bryan Gick
Professor, Director (ISRL Lab)

Najeeb Khan
Najeeb Khan
Adjunct Professor

Debasish Ray Mohapatra
Debasish Ray Mohapatra
PhD Student (HCT Lab)

Arian Shamei
Arian Shamei
PhD Student (ISRL Lab)

Yadong Liu
Yadong Liu
PhD Student (ISRL Lab)

Eric Easthope
Eric Easthope
M.A.Sc. Student (HCT Lab)

Yuanpei Gao
Yuanpei Gao
M.A.Sc. Student (HCT Lab)

Research

Talking Tube

Talking Tube

Vocal tract acoustic modelling using FDTD


Postural Speech Control

Postural Speech Control

Cortical evidence for speech motor articulatory settings


Continuous Generative Control

Continuous Generative Control

Speech motor control modelling using GANs


Moves Made Easy

Moves Made Easy

Human motor control effort reduction using deep learning with categorical perceptual constraints


null

Reaching task feedforward controller using reinforcement learning with soft actor-critic


Contact

Human Communication Technologies Lab
x427/x509, ICICS X-Wing
2366 Main Mall
Vancouver, BC, Canada
V6T 1Z4

Tel: +1 (604) 822-4583
Website: brain2speech.github.io
Email: ssfels at ece.ubc.ca

Publications

2021

Debasish Ray Mohapatra; Victor Zappi; Sidney Fels
A comparative study of two-dimensional vocal tract acoustic modeling based on Finite-Difference Time-Domain methods
arXiv preprint arXiv:2102.04588, 2021. [Article]
link / bibtex

Pramit Saha; Debasish Ray Mohapatra; Sidney Fels
SPEAK WITH YOUR HANDS Using Continuous Hand Gestures to control Articulatory Speech Synthesizer
arXiv preprint arXiv:2102.01640, 2021. [Article]
link / bibtex

2020

Bryan Gick; Connor Mayer; Chenhao Chiu; Erik Widing; Fran{ç}ois Roewer-Després; Sidney Fels; Ian Stavness
Quantal biomechanical effects in speech postures of the lips
Journal of neurophysiology, 2020. [Article]
link / bibtex

Pramit Saha; Yadong Liu; Bryan Gick; Sidney Fels
Ultra2speech-a deep learning framework for formant frequency estimation and tracking from ultrasound tongue images
International Conference on Medical Image Computing and Computer-Assisted Intervention, 2020. [Inproceedings]
link / bibtex