Implicit neural representations for time-frequency signal processing

Subramani, Krishna

Permalink

https://hdl.handle.net/2142/129827 Copy

Description

Title

Implicit neural representations for time-frequency signal processing

Author(s)

Subramani, Krishna

Issue Date

2025-06-24

Director of Research (if dissertation) or Advisor (if thesis)

Smaragdis, Paris

Doctoral Committee Chair(s)

Smaragdis, Paris

Committee Member(s)

• Kim, Minje
• Hasegawa-Johnson, Mark
• Choudhury, Romit Roy

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• time-frequency representations
• point clouds
• implicit neural representations
• multichannel filtering
• machine learning
• signal processing

Abstract

This dissertation presents a departure from conventional audio signal processing approaches that rely on fixed-dimensional vector representations and regularly sampled time-frequency grids. We introduce a flexible framework that models audio time-frequency representations using continuous, adaptive structures, enabling greater robustness and efficiency in modern applications. First, we propose a differentiable proxy for automatically optimizing Short-Time Fourier Transform parameters, aligning time-frequency resolution with task-specific objectives. We then reformulate time-frequency representations as Point Clouds, allowing for resolution-invariant processing and effective subsampling without sacrificing performance. Building on this foundation, we employ Implicit Neural Representations to model vectors and filters as continuous functions, thereby decoupling classical algorithms like multichannel filtering and matrix factorization from fixed parameters and sampling constraints. These contributions collectively propose a unified, parameter-agnostic view of signal processing that seamlessly integrates traditional methods with modern learning-based paradigms.

Graduation Semester

2025-08

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/129827

Copyright and License Information

Copyright 2025 Krishna Subramani

Owning Collections