Hainan Xu
16 papers · 2017–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🏃 Academic Marathon (8) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (5) 🐝 Cross-Pollinator (11)
🏃
Academic Marathon
(8)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(11)
🧬
Topic Evolution
🔥
Unstoppable
(5)
💎
Century Club
(16)
⚡
Prolific Year
(5)
🗃️
Keyword Collector
(76)
Conferences
INTERSPEECH (11)
EMNLP (2)
ACL (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
speech recognition
(5)
automatic speech recognition
(5)
neural network optimization
(2)
parallel corpus
(2)
logistic regression
(1)
weakly supervised learning
(1)
stochastic gradient descent
(1)
language model adaptation
(1)
text classification
(1)
topic modeling
(1)
neural machine translation
(1)
word alignment
(1)
speech enhancement
(1)
efficient inference
(1)
adversarial training
(1)
machine translation
(1)
matrix factorization
(1)
neural network compression
(1)
label smoothing
(1)
model compression
(1)
Papers
HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR
ICLR 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
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
Building State-of-the-art Distant Speech Recognition Using the CHiME-4 Challenge with a Setup of Speech Enhancement Baseline
INTERSPEECH 2018
Backstitch: Counteracting Finite-Sample Bias via Negative Steps
INTERSPEECH 2017
Zipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora
EMNLP 2017
The Kaldi OpenKWS System: Improving Low Resource Keyword Search
INTERSPEECH 2017