About George Close

I am a PhD candidate at the University of Sheffield, as part of the UKRI Centre for Doctoral Training in Speech and Language Technologies.
My supervisors are Dr. Stefan Goetze and Prof. Thomas Hain.
My project is sponsored in part by TOSHIBA Cambridge Research Laboratory.

Papers and Publications

• MetricGAN+/- Increasing Robustness of Noise Reduction on Unseen Data
  arXiv | EUSIPCO 2022 | Audio Examples

• Non-intrusive Speech Intelligibility Metric Prediction for Hearing Impaired Individuals - Clarity Prediction Challege 1
  INTERSPEECH 2022

• PAMGAN+/-: Improving Phase Aware Speech Enhancement Performance via Expanded Discriminator Training
  154th AES Convention Europe 2023
  🏆 WINNER: STUDENT TECHNICAL PAPER AWARD

• Perceive and predict: self-supervised speech representation based loss functions for speech enhancement
  arXiv | ICASSP 2023 | Audio Examples

• The Effect of Spoken Language on Speech Enhancement using Self-Supervised Speech Representation Loss Functions
  arXiv | WASPAA 2023 | GitHub

• Non Intrusive Intelligibility Predictor for Hearing Impaired Individuals using Self Supervised Speech Representations
  arXiv | Accepted @ ASRU SPARKS Workshop 2023
  

• Multi-CMGAN+/+: Leveraging Multi-Objective Speech Quality Metric Prediction for Speech Enhancement
  Techincal Report | Full paper accepted @ ICASSP 2024 | GitHub Entry to CHiME 2024 UDASE Task

• Non-Intrusive Speech Intelligibility Prediction for Hearing-Impaired Users using Intermediate ASR Features and Human Memory Models
  Techincal Report | Full paper accepted @ ICASSP 2024
  🏆 2nd Place in Clarity Prediction Challenge 2

Talks and Presentations

• AES [TC-MLAI] 2022 Talk -"Teaching AI to hear like we do: psychoacoustics in machine learning"

Interests

My research interests include:

• Neural Speech Enhancement / Noise Reduction
• Far Field Automatic Speech Recognition
• Speech Intelligibility Prediction
• Hearing Aid Design
• Speech Quality/Intelligibility Assessment Metrics
• Self Supervised Speech Representations

Technical Skills

• Python - PyTorch, SpeechBrain, SciPy
• CuDA
• MATLAB
• Linux/BASH
• C++, Java, Haskell

Qualifications/Background

Before starting at the CDT, I had completed an BSc undergraduate degree in Computer Science from Cardiff University, with a First Class Honours.