9 papers
Q-BWE: Quantum Chaos-Informed Speech Bandwidth Extension
Tarikul Islam Tamiti, Sajid Fardin Dipto, David Vergano +2
High-frequency reconstruction in bandwidth extension (BWE) depends on joined interactions among nonlinear spectral, temporal, and perceptual features; assigning a separate discrimi…
High Frequency Safeguard and Weighted Objective Scoring Bandwidth Extension
Tarikul Islam Tamiti, Sajid Fardin Dipto, Anomadarshi Barua
Speech Bandwidth Extension (BWE) reconstructs missing high frequencies from a band-limited signal. Please note that perceptually important information is often concentrated in shor…
Lyapunov-Inspired LyRIC Activation and GLARE Attention in Chaos-Guided State Space Modeling for EMG-To-Speech (ETS) Synthesis
Sajid Fardin Dipto, Tarikul Islam Tamiti, Luke Baja-Ricketts +2
Electromyography-to-Speech (ETS) synthesis is typically a non-linear, chaotic dynamical system. However, no prior work has studied the chaotic behavior of ETS synthesis to date. Ye…
BanglaBox: A Phonetically-Balanced Corpus and Data-Efficient Foundation-Model Adaptation for Bangla Text-to-Speech with Zero-Shot Voice Cloning
Emtiaz Uddin Ahmed, Araf Mahmud, Sajib Hossain +3
We present a recipe for adapting English-pretrained autoregressive TTS foundation models to underrepresented languages, demonstrated on Bangladeshi Bangla. Existing Bangla TTS corp…
SwinDS-BWE: A Parameter-Efficient Swin-1D Lattice Generator with Decision-Science Discriminators for Speech Bandwidth Extension
Tarikul Islam Tamiti, Sajid Fardin Dipto, Luke Baja-Ricketts +2
We propose SwinDS-BWE, a decision-science-inspired bandwidth extension (BWE) model with two coupled contributions: (1) Swin Transformers with lattice-style cross-stream interaction…
UDSS-BWE: Uncertainty- and Decision-Science Inspired Swin BandWidth Extension
Tarikul Islam Tamiti, Sajid Fardin Dipto, David Vergano +2
Bandwidth extension (BWE) is fundamentally localized: the most perceptual distortions are not average-case distortions, but rare high-frequency (HF) transients that standard, risk-…
CAPS: A Cascaded Reconstruction Model to Power Saving in Hearables Using Sub-Nyquist Sampling with Bandwidth Extension
Tarikul Islam Tamiti, Sajid Fardin Dipto, Luke Baja-Ricketts +2
Hearables are wearable computers worn on the ear. Bone conduction microphones are used with air conduction microphones in hearables for multimodal speech enhancement in noisy condi…
CS-ETS: Chaos-Inspired Samba-Based EMG-To-Speech Synthesis with Nonlinear Chaotic Losses
Sajid Fardin Dipto, Tarikul Islam Tamiti, David Vergano +2
We propose a chaos-inspired new architecture for EMG-to-Speech (ETS) synthesis called CS-ETS, which combines a Samba-based encoder with two novel chaos-inspired loss functions -- L…
SUBARU: A Practical Approach to Power Saving in Hearables Using SUB-Nyquist Audio Resolution Upsampling
Tarikul Islam Tamiti, Sajid Fardin Dipto, Luke Benjamin Baja-Ricketts +2
Hearables are wearable computers that are worn on the ear. Bone conduction microphones (BCMs) are used with air conduction microphones (ACMs) in hearables as a supporting modality…