Hainan Xu
19 papers · 2017–2025 · 5 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (31) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π§¬
Topic Evolution
π§
Keyword Pioneer
π
Renaissance Researcher
(5)
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(86)
Top co-authors
Research topics
Speech & Audio
(12)
Recognition
(12)
Machine Learning
(9)
Deep Learning
(7)
Natural Language Processing
(5)
Architectures
(5)
Application Areas
(4)
Applications
(4)
Core Methods
(3)
Learning Types
(3)
Optimization & Theory
(3)
Artificial Intelligence
(2)
Core AI
(2)
Computer Science
(1)
Computer Vision
(1)
Keywords
automatic speech recognition
(7)
speech recognition
(5)
word error rate
(2)
greedy decoding
(2)
neural network optimization
(2)
parallel corpus
(2)
speech translation
(2)
weakly supervised learning
(1)
logistic regression
(1)
stochastic gradient descent
(1)
topic modeling
(1)
neural machine translation
(1)
word alignment
(1)
language model adaptation
(1)
speech enhancement
(1)
text classification
(1)
efficient inference
(1)
machine translation
(1)
adversarial training
(1)
knowledge distillation
(1)
Papers
HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR
ICLR 2025
Pushing the Limits of Beam Search Decoding for Transducer-based ASR models
Interspeech 2025
WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection
Interspeech 2025
Word Level Timestamp Generation for Automatic Speech Recognition and Translation
Interspeech 2025
Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU
Interspeech 2024
Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts
Interspeech 2023
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
ICML 2023
Regularizing Word Segmentation by Creating Misspellings
Interspeech 2021
Multilingual Speech Recognition with Self-Attention Structured Parameterization
Interspeech 2020
Saliency-driven Word Alignment Interpretation for Neural Machine Translation
ACL 2019
The JHU ASR System for VOiCES from a Distance Challenge 2019
Interspeech 2019
A GPU-based WFST Decoder with Exact Lattice Generation
Interspeech 2018
Building State-of-the-art Distant Speech Recognition Using the CHiME-4 Challenge with a Setup of Speech Enhancement Baseline
Interspeech 2018
Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition
Interspeech 2018
Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks
Interspeech 2018
The JHU Parallel Corpus Filtering Systems for WMT 2018
EMNLP 2018
Backstitch: Counteracting Finite-Sample Bias via Negative Steps
Interspeech 2017
The Kaldi OpenKWS System: Improving Low Resource Keyword Search
Interspeech 2017
Zipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora
EMNLP 2017