Dr. Satwinder Singh profile picture

Hello, I'm

Dr. Satwinder Singh

Postdoctoral Research Fellow

Get To Know More

About Me

Profile picture
Experience icon

Experience

7+ years
Research & Teaching

Education icon

Education

PhD Computer Science
Massey University, NZ

Explore My

Experience

Technical Skills

Experience icon

Python

Expert

Experience icon

PyTorch

Expert

Experience icon

TensorFlow

Experienced

Experience icon

C/C++

Experienced

Experience icon

Linux

Experienced

Experience icon

SQL

Intermediate

Research Expertise

Experience icon

Speech Recognition

Expert

Experience icon

Deep Learning

Expert

Experience icon

NLP

Expert

Experience icon

AI Accessibility

Expert

What I've Been Up To

Recent Activities

Transformer workshop — intro session Transformer workshop — hands-on lab Transformer workshop — Q&A Transformer workshop — Q&A
October 2025
Part IV 2025
Part 4 Research students delivered outstanding work across a range of impactful topics and Secured best industry project in image and voice processing catrory 1 and 2.
Transformer workshop — intro session Transformer workshop — hands-on lab Transformer workshop — Q&A
September 2025
Transformer Models Workshop
Organized and led a one-day workshop on Transformer models with hands-on practical sessions at the University of Auckland.
ICASSP 2025 — keynote hall ICASSP 2025 — poster session ICASSP 2025 — demo area
April 2025
ICASSP 2025 Conference
Presented two papers on dysarthric speech recognition at the IEEE International Conference on Acoustics, Speech and Signal Processing in India.
ICONIP 2024 — venue ICONIP 2024 — talk session ICONIP 2024 — networking
December 2024
ICONIP 2024 Conference
Presented research on comprehensive performance evaluation of Whisper models in dysarthric speech recognition at ICONIP in New Zealand.
ACM MM Asia — conference hall ACM MM Asia — organizing team ACM MM Asia — registration desk
December 2024
Local Arrangement Chair
Served as Local Arrangement Chair for the ACM Multimedia Asia Conference held in Auckland, New Zealand.
Best Project Award — team photo Best Project Award — award ceremony Best Project Award — project demo
November 2024
Best Project Award
Supervised students Steven Li and Adi Shenoy who won the Best Project Award for developing a Neural Speaker Diarization System for Doctors.
Research supervision — meeting Research supervision — poster review Research supervision — experiment setup
Ongoing
PhD Student Supervision
Currently supervising multiple PhD and Honours students on projects related to dysarthric speech recognition, low-resource ASR, and AI accessibility tools.

Browse My

Recent Publications

2025
Convolution-Augmented Transformers for Enhanced Speaker-Independent Dysarthric Speech Recognition
Zihan Zhong, Qianli Wang, Satwinder Singh, Clarion Mendes, Mark Hasegawa-Johnson, Waleed Abdulla, Seyed Reza Shahamiri
IEEE Transactions on Neural Systems and Rehabilitation Engineering
Paper
2025
Convolution-Augmented Transformers for Enhanced Speaker-Independent Dysarthric Speech Recognition
Zihan Zhong, Qianli Wang, Satwinder Singh, Clarion Mendes, Mark Hasegawa-Johnson, Waleed Abdulla, Seyed Reza Shahamiri
IEEE Transactions on Neural Systems and Rehabilitation Engineering
Paper
2025
Robust Cross-Etiology and Speaker-Independent Dysarthric Speech Recognition
Satwinder Singh, Qianli Wang, Zihan Zhong, Clarion Mendes, Mark Hasegawa-Johnson, Waleed Abdulla, Seyed Reza Shahamiri
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), India, 2025
Paper
2025
Dysarthric Speech Conformer: Adaptation for Sequence-to-Sequence Dysarthric Speech Recognition
Qianli Wang, Zihan Zhong, Satwinder Singh, Clarion Mendes, Mark Hasegawa-Johnson, Waleed Abdulla, Seyed Reza Shahamiri
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), India, 2025
Paper
2024
A Comprehensive Performance Evaluation of Whisper Models in Dysarthric Speech Recognition
Satwinder Singh, Zihan Zhong, Qianli Wang, Clarion Mendes, Mark Hasegawa-Johnson, Waleed Abdulla, Seyed Reza Shahamiri
International Conference on Neural Information Processing (ICONIP), New Zealand, 2024
Paper
2023
PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognition
Chengxi Lei, Satwinder Singh*, Xiaoyun Jia, Feng Hou, Ruili Wang
ACM MM Asia, 2023
Paper
2023
Real and Synthetic Punjabi Speech Datasets for Speech Recognition
Satwinder Singh, Ruili Wang, Feng Hou
Data in Brief Journal, 2023
Paper Dataset
2023
A Novel Self-training Approach for Low-resource Speech Recognition
Satwinder Singh, Ruili Wang, Feng Hou
Proc. Interspeech, Ireland, pp. 1588-1592, 2023
Paper

Explore My

Featured Projects

Active
Dysarthric Speech Recognition System
Deep Learning • PyTorch • Accessibility
An end-to-end automatic speech recognition system designed specifically for dysarthric speech using convolution-augmented transformers. Achieves state-of-the-art performance across multiple etiology groups.
GitHub Download Demo
2024
Neural Speaker Diarization for Medical Consultations
Supervised Project • Audio Processing • Healthcare AI
Supervised development of an AI system to automatically identify and separate speakers in doctor-patient conversations. Developed by students Steven Li and Adi Shenoy, winning Best Project Award in 2024.
Watch Demo
Research
Te Reo Māori Speech Recognition
Low-Resource ASR • Transfer Learning • Cultural AI
Developing robust ASR models for te reo Māori using self-training and meta-learning approaches to overcome data scarcity. Collaborating with Māori language experts to ensure cultural appropriateness.
Paper
2023
Punjabi Speech Corpus
Dataset • Speech Synthesis • Open Source
Created comprehensive real and synthetic speech datasets for Punjabi language containing over 100 hours of annotated audio. Publicly available for research purposes on Mendeley Data.
Dataset Paper
2023
PhasePerturbation Augmentation
Data Augmentation • ASR Improvement • Signal Processing
Novel speech data augmentation technique using phase perturbation to improve ASR model robustness and generalization without requiring additional labeled data. Published at ACM MM Asia 2023.
Paper Code

Beyond Research

My Hobbies

When I'm not working on speech recognition algorithms, I love to express my creativity through watercolor painting. Painting allows me to unwind and see the world from a different perspective. Here are some of my recent watercolor works that capture moments of tranquility and beauty.

Watercolor Landscape
Soul on stroll
Watercolor on paper
Watercolor Sunset
Her
Watercolor on paper
Watercolor Flowers
Blooming Garden
Watercolor on paper
Watercolor Ocean
She said!
Watercolor on paper

Get in Touch

Contact Me

satwinder.singh@auckland.ac.nz

LinkedIn icon

LinkedIn