3 citations · 22 across the 18 of their papers we have counts for
20 papers
Scaling Neural Face Synthesis to High FPS and Low Latency by Neural Caching
Frank Yu, Sid Fels, Helge Rhodin
Recent neural rendering approaches greatly improve image quality, reaching near photorealism. However, the underlying neural networks have high runtime, precluding telepresence and…
A comparative study of two-dimensional vocal tract acoustic modeling based on Finite-Difference Time-Domain methods
Debasish Ray Mohapatra, Victor Zappi, Sidney Fels
The two-dimensional (2D) numerical approaches for vocal tract (VT) modelling can afford a better balance between the low computational cost and accurate rendering of acoustic wave…
SPEAK WITH YOUR HANDS Using Continuous Hand Gestures to control Articulatory Speech Synthesizer
Pramit Saha, Debasish Ray Mohapatra, Sidney Fels
This work presents our advancements in controlling an articulatory speech synthesis engine, \textit{viz.}, Pink Trombone, with hand gestures. Our interface translates continuous fi…
Ultra2Speech -- A Deep Learning Framework for Formant Frequency Estimation and Tracking from Ultrasound Tongue Images
Pramit Saha, Yadong Liu, Bryan Gick +1
Thousands of individuals need surgical removal of their larynx due to critical diseases every year and therefore, require an alternative form of communication to articulate speech…
Learning Joint Articulatory-Acoustic Representations with Normalizing Flows
Pramit Saha, Sidney Fels
The articulatory geometric configurations of the vocal tract and the acoustic properties of the resultant speech sound are considered to have a strong causal relationship. This pap…
Variational Learning with Disentanglement-PyTorch
Amir H. Abdi, Purang Abolmaesumi, Sidney Fels
Unsupervised learning of disentangled representations is an open problem in machine learning. The Disentanglement-PyTorch library is developed to facilitate research, implementatio…
A Study into Echocardiography View Conversion
Amir H. Abdi, Mohammad H. Jafari, Sidney Fels +2
Transthoracic echo is one of the most common means of cardiac studies in the clinical routines. During the echo exam, the sonographer captures a set of standard cross sections (ech…
A Preliminary Study of Disentanglement With Insights on the Inadequacy of Metrics
Amir H. Abdi, Purang Abolmaesumi, Sidney Fels
Disentangled encoding is an important step towards a better representation learning. However, despite the numerous efforts, there still is no clear winner that captures the indepen…
Reinforcement Learning for High-dimensional Continuous Control in Biomechanics: An Intro to ArtiSynth-RL
Amir H. Abdi, Masoud Malakoutian, Thomas Oxland +1
Neural control is an exciting mystery which we instinctively master. Yet, researchers have a hard time explaining the motor control trajectories. Physiologically accurate biomechan…
EEG-to-F0: Establishing artificial neuro-muscular pathway for kinematics-based fundamental frequency control
Himanshu Goyal, Pramit Saha, Bryan Gick +1
The fundamental frequency (F0) of human voice is generally controlled by changing the vocal fold parameters (including tension, length and mass), which in turn is manipulated by th…
An extended two-dimensional vocal tract model for fast acoustic simulation of single-axis symmetric three-dimensional tubes
Debasish Ray Mohapatra, Victor Zappi, Sidney Fels
The simulation of two-dimensional (2D) wave propagation is an affordable computational task and its use can potentially improve time performance in vocal tracts' acoustic analysis.…
Variational Shape Completion for Virtual Planning of Jaw Reconstructive Surgery
Amir H. Abdi, Mehran Pesteie, Eitan Prisman +2
The premorbid geometry of the mandible is of significant relevance in jaw reconstructive surgeries and occasionally unknown to the surgical team. In this paper, an optimization fra…
SPEAK YOUR MIND! Towards Imagined Speech Recognition With Hierarchical Deep Learning
Pramit Saha, Muhammad Abdul-Mageed, Sidney Fels
Speech-related Brain Computer Interface (BCI) technologies provide effective vocal communication strategies for controlling devices through speech commands interpreted from brain s…
Deep Learning the EEG Manifold for Phonological Categorization from Active Thoughts
Pramit Saha, Muhammad Abdul-Mageed, Sidney Fels
Speech-related Brain Computer Interfaces (BCI) aim primarily at finding an alternative vocal communication pathway for people with speaking disabilities. As a step towards full dec…
Hierarchical Deep Feature Learning For Decoding Imagined Speech From EEG
Pramit Saha, Sidney Fels
We propose a mixed deep neural network strategy, incorporating parallel combination of Convolutional (CNN) and Recurrent Neural Networks (RNN), cascaded with deep autoencoders and…
Sound-Stream II: Towards Real-Time Gesture Controlled Articulatory Sound Synthesis
Pramit Saha, Debasish Ray Mohapatra, Praneeth SV +1
We present an interface involving four degrees-of-freedom (DOF) mechanical control of a two dimensional, mid-sagittal tongue through a biomechanical toolkit called ArtiSynth and a…
Limitations of Source-Filter Coupling In Phonation
Debasish Ray Mohapatra, Sidney Fels
The coupling of vocal fold (source) and vocal tract (filter) is one of the most critical factors in source-filter articulation theory. The traditional linear source-filter theory h…
Muscle Excitation Estimation in Biomechanical Simulation Using NAF Reinforcement Learning
Amir H. Abdi, Pramit Saha, Praneeth Srungarapu +1
Motor control is a set of time-varying muscle excitations which generate desired motions for a biomechanical system. Muscle excitations cannot be directly measured from live subjec…
Towards Automatic Speech Identification from Vocal Tract Shape Dynamics in Real-time MRI
Pramit Saha, Praneeth Srungarapu, Sidney Fels
Vocal tract configurations play a vital role in generating distinguishable speech sounds, by modulating the airflow and creating different resonant cavities in speech production. T…
Spectral Study of the Vocal Tract in Vowel Synthesis: A Comparison between 1D and 3D Acoustic Analysis
Negar M. Harandi, Daniel Aalto, Antti Hannukainen +2
A state-of-the-art 1D acoustic synthesizer has been previously developed, and coupled to speaker-specific biomechanical models of oropharynx in ArtiSynth. As expected, the formant…