Mathew Magimai Doss
8 papers · 2022–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(20)
⚡
Prolific Year · Productive
🌈
Renaissance Researcher
(7)
Venues
Top co-authors
Research topics
Deep Learning
(4)
Speech & Audio
(4)
Analysis
(4)
Artificial Intelligence
(3)
Machine Learning
(3)
Core AI
(3)
Architectures
(2)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Computer Vision
(1)
Healthcare & Medicine
(1)
Interdisciplinary
(1)
Mathematics & Optimization
(1)
Security & Privacy
(1)
Clinical
(1)
Keywords
zero-shot learning
(1)
self-supervised learning
(1)
voice conversion
(1)
speech synthesis
(1)
speech processing
(1)
automatic speech recognition
(1)
speaker embedding
(1)
parkinson's disease
(1)
speech classification
(1)
synthetic speech detection
(1)
deep metric learning
(1)
multimodal fusion
(1)
utility metric
(1)
text-to-speech synthesis
(1)
power spectral density
(1)
multilingual embedding
(1)
neural embedding
(1)
word error rate
(1)
subjective evaluation
(1)
unsupervised learning
(1)
Papers
Children's Voice Privacy: First Steps and Emerging Challenges
Interspeech 2025
kNN Retrieval for Simple and Effective Zero-Shot Multi-speaker Text-to-Speech
NAACL 2025
Multimodal Prosody Modeling: A Use Case for Multilingual Sentence Mode Prediction
Interspeech 2025
Speech power spectra: a window into neural oscillations in Parkinson's disease
Interspeech 2025
Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech
Interspeech 2025
Unveiling Audio Deepfake Origins: A Deep Metric learning And Conformer Network Approach With Ensemble Fusion
Interspeech 2025
On Breathing Pattern Information in Synthetic Speech
Interspeech 2022
Unsupervised Voice Activity Detection by Modeling Source and System Information using Zero Frequency Filtering
Interspeech 2022