← Authors

Athanasios Mouchtaris

21 papers · 2020–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (5) 🐝 Cross-Pollinator (10) 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (35) πŸ”¬ Deep Specialist (10) πŸ—ƒοΈ Keyword Collector (83) πŸ’Ž Century Club (21) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (6) ⚑ Prolific Year (6)

Conferences

INTERSPEECH (14) EMNLP (4) ACL (1) ICLR (1) ICML (1)

Top co-authors

Martin Radfar (7) Kai Zhen (7) Nathan Susanj (7) Zheng Zhang (5) Rupak Vignesh Swaminathan (4) Ariya Rastrow (4) Siegfried Kunzmann (4) Grant P. Strimel (4) Yifan Yang (4) Yi Xie (3)

Keywords

automatic speech recognition (6) model compression (5) recurrent neural network transducer (5) end-to-end speech recognition (4) spoken language understanding (4) model quantization (3) zeroth-order optimization (3) memory efficiency (3) voice assistant (2) streaming speech recognition (2) transformer transducer (2) knowledge distillation (2) speech recognition (2) multi-task learning (2) long short-term memory (2) slot filling (2) low latency (2) intent classification (2) quantization-aware training (2) large language model (2)

Papers

Wanda++: Pruning Large Language Models via Regional Gradients ACL 2025
QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models EMNLP 2025
MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models EMNLP 2025
Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models EMNLP 2025
Context-aware Dynamic Pruning for Speech Foundation Models ICLR 2025
AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning EMNLP 2024
Conmer: Streaming Conformer Without Self-attention for Interactive Voice Assistants INTERSPEECH 2023
Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers ICML 2023
ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition INTERSPEECH 2022
Knowledge Distillation via Module Replacing for Automatic Speech Recognition with Recurrent Neural Network Transducer INTERSPEECH 2022
Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition INTERSPEECH 2022
Compute Cost Amortized Transformer for Streaming ASR INTERSPEECH 2022
FANS: Fusing ASR and NLU for On-Device SLU INTERSPEECH 2021
Phonetically Induced Subwords for End-to-End Speech Recognition INTERSPEECH 2021
CoDERT: Distilling Encoder Representations with Co-Learning for Transducer-Based Speech Recognition INTERSPEECH 2021
End-to-End Spoken Language Understanding for Generalized Voice Assistants INTERSPEECH 2021
Multi-Channel Transformer Transducer for Speech Recognition INTERSPEECH 2021
Evaluating the Vulnerability of End-to-End Automatic Speech Recognition Models to Membership Inference Attacks INTERSPEECH 2021
End-to-End Neural Transformer Based Spoken Language Understanding INTERSPEECH 2020
Semantic Complexity in End-to-End Spoken Language Understanding INTERSPEECH 2020
Quantization Aware Training with Absolute-Cosine Regularization for Automatic Speech Recognition INTERSPEECH 2020