← Authors

Deliang Wang

36 papers · 2012–2025 · 4 conferences · across top CS/AI conferences

Achievements

πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (4) πŸƒ Academic Marathon (13) 🌈 Renaissance Researcher (7) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (14) 🐝 Cross-Pollinator (14) 🧭 Keyword Pioneer 🏠 Conference Loyalist (31) πŸ† Keyword Champion (2) πŸ”¬ Deep Specialist (17) 🧬 Topic Evolution πŸ—ƒοΈ Keyword Collector (144) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter πŸ’Ž Century Club (36) πŸ”₯ Unstoppable (10) ⚑ Prolific Year (6)

Conferences

INTERSPEECH (31) AAAI (2) ACL (2) NIPS (1)

Top co-authors

Ashutosh Pandey (8) Hao Zhang (6) Zhong-Qiu Wang (5) Ke Tan (5) Buye Xu (4) Xueliang Zhang (3) Hassan Taherian (3) Gaowei Chen (3) Qiao Tian (2) Anurag Kumar (2)

Research topics

Techniques (1) Education (1)

Keywords

speech enhancement (9) speech separation (8) long short-term memory (6) deep learning (6) convolutional recurrent network (5) speaker separation (5) deep neural network (5) multi-channel processing (4) signal-to-noise ratio (3) active noise control (3) automatic speech recognition (3) source separation (3) time-frequency masking (3) spectral feature (3) acoustic echo cancellation (3) speech intelligibility (3) permutation invariant training (3) supervised learning (2) neural vocoder (2) reverberant speech (2)

Papers

Extended LSTMs for Knowledge Tracing: Peeking Inside the Black Box (Student Abstract) AAAI 2025
Wonderland_EDU@HKU at BEA 2025 Shared Task: Fine-tuning Large Language Models to Evaluate the Pedagogical Ability of AI-powered Tutors ACL 2025
Towards Explainable Monaural Speaker Separation with Auditory-based Training INTERSPEECH 2024
On the Interpretability of Deep Learning Models for Collaborative Argumentation Analysis in Classrooms ACL 2024
Opening the Black Box: Unraveling the Classroom Dialogue Analysis (Student Abstract) AAAI 2024
Time-domain Transformer-based Audiovisual Speaker Separation INTERSPEECH 2023
Time-Domain Speech Enhancement for Robust Automatic Speech Recognition INTERSPEECH 2023
Multi-input Multi-output Complex Spectral Mapping for Speaker Separation INTERSPEECH 2023
Neural Vocoder is All You Need for Speech Super-resolution INTERSPEECH 2022
VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration INTERSPEECH 2022
Attentive Recurrent Network for Low-Latency Active Noise Control INTERSPEECH 2022
Time-domain Ad-hoc Array Speech Enhancement Using a Triple-path Network INTERSPEECH 2022
Densely-connected Convolutional Recurrent Network for Fundamental Frequency Estimation in Noisy Speech INTERSPEECH 2022
Attentive Training: A New Training Framework for Talker-independent Speaker Extraction INTERSPEECH 2022
A Deep Learning Approach to Multi-Channel and Multi-Microphone Acoustic Echo Cancellation INTERSPEECH 2021
A Deep Learning Method to Multi-Channel Active Noise Control INTERSPEECH 2021
Noisy-Reverberant Speech Enhancement Using DenseUNet with Time-Frequency Attention INTERSPEECH 2020
A Deep Learning Approach to Active Noise Control INTERSPEECH 2020
Frame-Level Signal-to-Noise Ratio Estimation Using Deep Learning INTERSPEECH 2020
Learning Complex Spectral Mapping for Speech Enhancement with Improved Cross-Corpus Generalization INTERSPEECH 2020
Deep Learning Based Multi-Channel Speaker Recognition in Noisy and Reverberant Environments INTERSPEECH 2019
Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling INTERSPEECH 2019
Enhanced Spectral Features for Distortion-Independent Acoustic Modeling INTERSPEECH 2019
Deep Learning for Joint Acoustic Echo and Noise Cancellation with Nonlinear Distortions INTERSPEECH 2019
Robust TDOA Estimation Based on Time-Frequency Masking and Deep Neural Networks INTERSPEECH 2018
A Two-Stage Approach to Noisy Cochannel Speech Separation with Gated Residual Networks INTERSPEECH 2018
Deep Learning for Acoustic Echo Cancellation in Noisy and Double-Talk Scenarios INTERSPEECH 2018
All-Neural Multi-Channel Speech Enhancement INTERSPEECH 2018
A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement INTERSPEECH 2018
Integrating Spectral and Spatial Features for Multi-Channel Speaker Separation INTERSPEECH 2018
End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction INTERSPEECH 2018
A New Framework for Supervised Speech Enhancement in the Time Domain INTERSPEECH 2018
Binaural Reverberant Speech Separation Based on Deep Neural Networks INTERSPEECH 2017
A Feature Study for Masking-Based Reverberant Speech Separation INTERSPEECH 2016
Long Short-Term Memory for Speaker Generalization in Supervised Speech Separation INTERSPEECH 2016
Cocktail Party Processing via Structured Prediction NIPS 2012