Ahmed Hussen Abdelaziz
11 papers · 2016–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (17) π§ Keyword Pioneer π Conference Polyglot (2) π Academic Marathon (9) π Cross-Pollinator (9)
π
Interdisciplinary Bridge
π
Conference Pioneer
β
The Questioner
π
Trend Setter
π
Century Club
(11)
Conferences
INTERSPEECH (10)
ICML (1)
Top co-authors
Keywords
multimodal learning
(4)
parameter efficiency
(2)
audio-visual speech recognition
(2)
speech detection
(2)
self-supervised learning
(2)
automatic speech recognition
(2)
turbo decoding
(2)
speaker verification
(2)
acoustic model
(1)
weakly-supervised learning
(1)
acoustic modeling
(1)
speaker recognition
(1)
error rate
(1)
knowledge distillation
(1)
hidden markov model
(1)
speaker embedding
(1)
speech intelligibility
(1)
low-rank adaptation
(1)
forward-backward algorithm
(1)
speech enhancement
(1)
Papers
A Variational Framework for Improving Naturalness in Generative Spoken Language Models
ICML 2025
Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection
INTERSPEECH 2024
ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
INTERSPEECH 2024
Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?
INTERSPEECH 2024
Comparative Analysis of Personalized Voice Activity Detection Systems: Assessing Real-World Effectiveness
INTERSPEECH 2024
Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models
INTERSPEECH 2022
NTCD-TIMIT: A New Database and Baseline for Noise-Robust Audio-Visual Speech Recognition
INTERSPEECH 2017
Turbo Decoders for Audio-Visual Continuous Speech Recognition
INTERSPEECH 2017
Blind Non-Intrusive Speech Intelligibility Prediction Using Twin-HMMs
INTERSPEECH 2016
Introducing the Turbo-Twin-HMM for Audio-Visual Speech Enhancement
INTERSPEECH 2016
Dynamic Stream Weighting for Turbo-Decoding-Based Audiovisual ASR
INTERSPEECH 2016