← Authors

Shaojun Wang

45 papers · 2003–2025 · 13 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (22) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (9) 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (13) πŸ—ΊοΈ Taxonomy Completionist (21) πŸ† Keyword Champion 🌱 Topic Pioneer 🀝 Dynamic Duo (31) πŸ—ƒοΈ Keyword Collector (54) πŸ’Ž Century Club (45) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer πŸ”₯ Unstoppable (7) ⚑ Prolific Year (11)

Conferences

INTERSPEECH (15) ACL (6) EMNLP (5) NIPS (4) AISTATS (2) ICML (2) IJCAI (2) IJCNLP (2) NAACL (2) SEMEVAL (2) AAAI (1) COLING (1) EACL (1)

Top co-authors

Jing Xiao (31) Jun Ma (11) Minchuan Chen (11) Yanmeng Wang (9) Ye Wang (9) Chenfeng Miao (7) Dale Schuurmans (6) Tian Xia (5) Wei Hu (4) Tao Wei (4)

Keywords

attention mechanism (6) semi-supervised learning (3) pre-trained language model (3) generative adversarial network (3) parameter efficiency (2) chinese spelling check (2) non-autoregressive model (2) automatic speech recognition (2) machine reading comprehension (2) transfer learning (2) multi-label classification (2) voice conversion (2) speech recognition (2) neural vocoder (2) reading comprehension (2) speech synthesis (2) language model (2) question answering (2) data augmentation (2) abstract meaning (2)

Papers

GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression EMNLP 2025
ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents ACL 2025
Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models ACL 2025
Improving Multilingual Text-to-Speech with Mixture-of-Language-Experts and Accent Disentanglement INTERSPEECH 2024
E-Paraformer: A Faster and Better Parallel Transformer for Non-autoregressive End-to-End Mandarin Speech Recognition INTERSPEECH 2024
DFlow: A Generative Model Combining Denoising AutoEncoder and Normalizing Flow for High Fidelity Waveform Generation ICML 2024
Exploring multi-task learning and data augmentation in dementia detection with self-supervised pretrained models INTERSPEECH 2023
Improving End-to-End Modeling For Mandarin-English Code-Switching Using Lightweight Switch-Routing Mixture-of-Experts INTERSPEECH 2023
FFM: A Frame Filtering Mechanism To Accelerate Inference Speed For Conformer In Speech Recognition INTERSPEECH 2022
A compact transformer-based GAN vocoder INTERSPEECH 2022
Learning to Adapt to Low-Resource Paraphrase Generation EMNLP 2022
PINGAN Omini-Sinitic at SemEval-2022 Task 4: Multi-prompt Training for Patronizing and Condescending Language Detection SEMEVAL 2022
Towards Efficiently Learning Monotonic Alignments for Attention-based End-to-End Speech Recognition INTERSPEECH 2022
PINGAN Omini-Sinitic at SemEval-2022 Task 4: Multi-prompt Training for Patronizing and Condescending Language Detection NAACL 2022
Adversarial Knowledge Distillation For Robust Spoken Language Understanding INTERSPEECH 2022
PINGAN Omini-Sinitic at SemEval-2021 Task 4:Reading Comprehension of Abstract Meaning IJCNLP 2021
Learning Speech Structure to Improve Time-Frequency Masks INTERSPEECH 2021
EfficientSing: A Chinese Singing Voice Synthesis System Using Duration-Free Acoustic Model and HiFi-GAN Vocoder INTERSPEECH 2021
PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check ACL 2021
PINGAN Omini-Sinitic at SemEval-2021 Task 4:Reading Comprehension of Abstract Meaning ACL 2021
Understanding Gradient Clipping In Incremental Gradient Methods AISTATS 2021
Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval EMNLP 2021
EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture ICML 2021
PINGAN Omini-Sinitic at SemEval-2021 Task 4:Reading Comprehension of Abstract Meaning SEMEVAL 2021
PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check IJCNLP 2021
Improving Polyphone Disambiguation for Mandarin Chinese by Combining Mix-Pooling Strategy and Window-Based Attention INTERSPEECH 2021
Nonparallel Emotional Speech Conversion Using VAE-GAN INTERSPEECH 2020
An Iterative Polishing Framework Based on Quality Aware Masked Language Model for Chinese Poetry Generation AAAI 2020
Generating Reasonable Legal Text through the Combination of Language Modeling and Question Answering IJCAI 2020
Improving Replay Detection System with Channel Consistency DenseNeXt for the ASVspoof 2019 Challenge INTERSPEECH 2020
Non-Parallel Voice Conversion with Fewer Labeled Data by Conditional Generative Adversarial Networks INTERSPEECH 2020
Adversarial Discrete Sequence Generation without Explicit NeuralNetworks as Discriminators AISTATS 2019
Cross-Lingual, Multi-Speaker Text-To-Speech Synthesis Using Neural Speaker Embedding INTERSPEECH 2019
A Direct Boosting Approach for Semi-supervised Classification IJCAI 2015
Improving Alignment of System Combination by Using Multi-objective Optimization EMNLP 2013
Direct 0-1 Loss Minimization and Margin Maximization with Boosting NIPS 2013
A Corpus Level MIRA Tuning Strategy for Machine Translation EMNLP 2013
A Large Scale Distributed Syntactic, Semantic and Lexical Language Model for Machine Translation ACL 2011
A Rate Distortion Approach for Semi-Supervised Conditional Random Fields NIPS 2009
implicit Online Learning with Kernels NIPS 2006
Semi-Supervised Conditional Random Fields for Improved Sequence Segmentation and Labeling COLING 2006
Semi-Supervised Conditional Random Fields for Improved Sequence Segmentation and Labeling ACL 2006
Learning to Model Spatial Dependency: Semi-Supervised Discriminative Random Fields NIPS 2006
Language Independent Authorship Attribution with Character Level N-Grams EACL 2003
Language and Task Independent Text Categorization with Simple Language Models NAACL 2003