Hainan Xu - RankMe

60 papers A* 3A 17B 1C 3Misc 8Journal 22Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Chunk-wise Attention Transducers for Fast and Accurate Streaming Speech-to-Text. CoRR Hainan Xu, Vladimir Bataev, Travis M. Bartley, Jagadeesh Balam
2025	A*	`conf`	HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR. ICLR Hainan Xu, Travis M. Bartley, Vladimir Bataev, Boris Ginsburg
2025	A	`conf`	Pushing the Limits of Beam Search Decoding for Transducer-based ASR models. INTERSPEECH Lilit Grigoryan, Vladimir Bataev, Andrei Andrusenko, Hainan Xu, Vitaly Lavrukhin, Boris Ginsburg
2025	J	`jnl`	Pushing the Limits of Beam Search Decoding for Transducer-based ASR models. CoRR Lilit Grigoryan, Vladimir Bataev, Andrei Andrusenko, Hainan Xu, Vitaly Lavrukhin, Boris Ginsburg
2025	A	`conf`	WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection. INTERSPEECH Hainan Xu, Vladimir Bataev, Lilit Grigoryan, Boris Ginsburg
2025	J	`jnl`	WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection. CoRR Hainan Xu, Vladimir Bataev, Lilit Grigoryan, Boris Ginsburg
2025	A	`conf`	Word Level Timestamp Generation for Automatic Speech Recognition and Translation. INTERSPEECH Ke Hu, Krishna C. Puvvada, Elena Rastorgueva, Zhehuai Chen, He Huang, Shuoyang Ding, Kunal Dhawan, Hainan Xu, Jagadeesh Balam, Boris Ginsburg
2025	J	`jnl`	Word Level Timestamp Generation for Automatic Speech Recognition and Translation. CoRR Ke Hu, Krishna C. Puvvada, Elena Rastorgueva, Zhehuai Chen, He Huang, Shuoyang Ding, Kunal Dhawan, Hainan Xu, Jagadeesh Balam, Boris Ginsburg
2024	—	`conf`	Label-Looping: Highly Efficient Decoding For Transducers. SLT Vladimir Bataev, Hainan Xu, Daniel Galvez, Vitaly Lavrukhin, Boris Ginsburg
2024	J	`jnl`	Label-Looping: Highly Efficient Decoding for Transducers. CoRR Vladimir Bataev, Hainan Xu, Daniel Galvez, Vitaly Lavrukhin, Boris Ginsburg
2024	—	`conf`	Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation. SLT Nithin Rao Koluguri, Travis M. Bartley, Hainan Xu, Oleksii Hrinchuk, Jagadeesh Balam, Boris Ginsburg, Georg Kucsko
2024	J	`jnl`	Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation. CoRR Nithin Rao Koluguri, Travis M. Bartley, Hainan Xu, Oleksii Hrinchuk, Jagadeesh Balam, Boris Ginsburg, Georg Kucsko
2024	—	`conf`	Romanization Encoding For Multilingual ASR. SLT Wen Ding, Fei Jia, Hainan Xu, Yu Xi, Junjie Lai, Boris Ginsburg
2024	J	`jnl`	Romanization Encoding For Multilingual ASR. CoRR Wen Ding, Fei Jia, Hainan Xu, Yu Xi, Junjie Lai, Boris Ginsburg
2024	A	`conf`	Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU. INTERSPEECH Daniel Galvez, Vladimir Bataev, Hainan Xu, Tim Kaldewey
2024	J	`jnl`	Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU. CoRR Daniel Galvez, Vladimir Bataev, Hainan Xu, Tim Kaldewey
2024	J	`jnl`	TDT-KWS: Fast And Accurate Keyword Spotting Using Token-and-duration Transducer. CoRR Yu Xi, Hao Li, Baochen Yang, Haoyu Li, Hainan Xu, Kai Yu
2024	Misc	`conf`	TDT-KWS: Fast and Accurate Keyword Spotting Using Token-and-Duration Transducer. ICASSP Yu Xi, Hao Li, Baochen Yang, Haoyu Li, Hainan Xu, Kai Yu
2024	J	`jnl`	Three-in-One: Fast and Accurate Transducer for Hybrid-Autoregressive ASR. CoRR Hainan Xu, Travis M. Bartley, Vladimir Bataev, Boris Ginsburg
2024	Misc	`conf`	Transducers with Pronunciation-Aware Embeddings for Automatic Speech Recognition. ICASSP Hainan Xu, Zhehuai Chen, Fei Jia, Boris Ginsburg
2024	J	`jnl`	Transducers with Pronunciation-aware Embeddings for Automatic Speech Recognition. CoRR Hainan Xu, Zhehuai Chen, Fei Jia, Boris Ginsburg
2023	A	`conf`	Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts. INTERSPEECH Dongji Gao, Matthew Wiesner, Hainan Xu, Leibny Paola García, Daniel Povey, Sanjeev Khudanpur
2023	J	`jnl`	Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts. CoRR Dongji Gao, Matthew Wiesner, Hainan Xu, Leibny Paola García, Daniel Povey, Sanjeev Khudanpur
2023	A*	`conf`	Efficient Sequence Transduction by Jointly Predicting Tokens and Durations. ICML Hainan Xu, Fei Jia, Somshubra Majumdar, He Huang, Shinji Watanabe, Boris Ginsburg
2023	J	`jnl`	Efficient Sequence Transduction by Jointly Predicting Tokens and Durations. CoRR Hainan Xu, Fei Jia, Somshubra Majumdar, He Huang, Shinji Watanabe, Boris Ginsburg
2023	C	`conf`	Learning From Flawed Data: Weakly Supervised Automatic Speech Recognition. ASRU Dongji Gao, Hainan Xu, Desh Raj, Leibny Paola García-Perera, Daniel Povey, Sanjeev Khudanpur
2023	J	`jnl`	Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition. CoRR Dongji Gao, Hainan Xu, Desh Raj, Leibny Paola García-Perera, Daniel Povey, Sanjeev Khudanpur
2023	Misc	`conf`	Multi-Blank Transducers for Speech Recognition. ICASSP Hainan Xu, Fei Jia, Somshubra Majumdar, Shinji Watanabe, Boris Ginsburg
2022	J	`jnl`	Modeling the Dynamics of a Ratio-Dependent Leslie-Gower Predator-Prey System with Strong Allee Effect. Int. J. Bifurc. Chaos Hainan Xu, Daihai He
2022	J	`jnl`	Multi-blank Transducers for Speech Recognition. CoRR Hainan Xu, Fei Jia, Somshubra Majumdar, Shinji Watanabe, Boris Ginsburg
2021	J	`jnl`	An Asynchronous WFST-Based Decoder For Automatic Speech Recognition. CoRR Hang Lv, Zhehuai Chen, Hainan Xu, Daniel Povey, Lei Xie, Sanjeev Khudanpur
2021	Misc	`conf`	An Asynchronous WFST-Based Decoder for Automatic Speech Recognition. ICASSP Hang Lv, Zhehuai Chen, Hainan Xu, Daniel Povey, Lei Xie, Sanjeev Khudanpur
2021	Misc	`conf`	Convolutional Dropout and Wordpiece Augmentation for End-to-End Speech Recognition. ICASSP Hainan Xu, Yinghui Huang, Yun Zhu, Kartik Audhkhasi, Bhuvana Ramabhadran
2021	A	`conf`	Regularizing Word Segmentation by Creating Misspellings. Interspeech Hainan Xu, Kartik Audhkhasi, Yinghui Huang, Jesse Emond, Bhuvana Ramabhadran
2020	A	`conf`	Multilingual Speech Recognition with Self-Attention Structured Parameterization. INTERSPEECH Yun Zhu, Parisa Haghani, Anshuman Tripathi, Bhuvana Ramabhadran, Brian Farris, Hainan Xu, Han Lu, Hasim Sak, Isabel Leal, Neeraj Gaur, Pedro J. Moreno, Qian Zhang
2019	C	`conf`	Espresso: A Fast End-to-End Neural Speech Recognition Toolkit. ASRU Yiming Wang, Sanjeev Khudanpur, Tongfei Chen, Hainan Xu, Shuoyang Ding, Hang Lv, Yiwen Shao, Nanyun Peng, Lei Xie, Shinji Watanabe
2019	J	`jnl`	Espresso: A Fast End-to-end Neural Speech Recognition Toolkit. CoRR Yiming Wang, Tongfei Chen, Hainan Xu, Shuoyang Ding, Hang Lv, Yiwen Shao, Nanyun Peng, Lei Xie, Shinji Watanabe, Sanjeev Khudanpur
2019	Misc	`conf`	Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling. ICASSP Hainan Xu, Shuoyang Ding, Shinji Watanabe
2019	C	`conf`	Incremental Lattice Determinization for WFST Decoders. ASRU Zhehuai Chen, Mahsa Yarmohammadi, Hainan Xu, Hang Lv, Lei Xie, Daniel Povey, Sanjeev Khudanpur
2019	—	`conf`	Robust Document Representations for Cross-Lingual Information Retrieval in Low-Resource Settings. MTSummit (1) Mahsa Yarmohammadi, Xutai Ma, Sorami Hisamoto, Muhammad Rahman, Yiming Wang, Hainan Xu, Daniel Povey, Philipp Koehn, Kevin Duh
2019	—	`conf`	Saliency-driven Word Alignment Interpretation for Neural Machine Translation. WMT (1) Shuoyang Ding, Hainan Xu, Philipp Koehn
2019	J	`jnl`	Saliency-driven Word Alignment Interpretation for Neural Machine Translation. CoRR Shuoyang Ding, Hainan Xu, Philipp Koehn
2019	A	`conf`	The JHU ASR System for VOiCES from a Distance Challenge 2019. INTERSPEECH Yiming Wang, David Snyder, Hainan Xu, Vimal Manohar, Phani Sankar Nidadavolu, Daniel Povey, Sanjeev Khudanpur
2018	A	`conf`	A GPU-based WFST Decoder with Exact Lattice Generation. INTERSPEECH Zhehuai Chen, Justin Luitjens, Hainan Xu, Yiming Wang, Daniel Povey, Sanjeev Khudanpur
2018	J	`jnl`	A GPU-based WFST Decoder with Exact Lattice Generation. CoRR Zhehuai Chen, Justin Luitjens, Hainan Xu, Yiming Wang, Daniel Povey, Sanjeev Khudanpur
2018	Misc	`conf`	A Pruned Rnnlm Lattice-Rescoring Algorithm for Automatic Speech Recognition. ICASSP Hainan Xu, Tongfei Chen, Dongji Gao, Yiming Wang, Ke Li, Nagendra Goel, Yishay Carmiel, Daniel Povey, Sanjeev Khudanpur
2018	A	`conf`	Building State-of-the-art Distant Speech Recognition Using the CHiME-4 Challenge with a Setup of Speech Enhancement Baseline. INTERSPEECH Szu-Jui Chen, Aswin Shanmugam Subramanian, Hainan Xu, Shinji Watanabe
2018	J	`jnl`	Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline. CoRR Szu-Jui Chen, Aswin Shanmugam Subramanian, Hainan Xu, Shinji Watanabe
2018	J	`jnl`	Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling. CoRR Hainan Xu, Shuoyang Ding, Shinji Watanabe
2018	Misc	`conf`	Neural Network Language Modeling with Letter-Based Features and Importance Sampling. ICASSP Hainan Xu, Ke Li, Yiming Wang, Jian Wang, Shiyin Kang, Xie Chen, Daniel Povey, Sanjeev Khudanpur
2018	A	`conf`	Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition. INTERSPEECH Ke Li, Hainan Xu, Yiming Wang, Daniel Povey, Sanjeev Khudanpur
2018	A	`conf`	Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks. INTERSPEECH Daniel Povey, Gaofeng Cheng, Yiming Wang, Ke Li, Hainan Xu, Mahsa Yarmohammadi, Sanjeev Khudanpur
2018	—	`conf`	The JHU Parallel Corpus Filtering Systems for WMT 2018. WMT (shared task) Huda Khayrallah, Hainan Xu, Philipp Koehn
2017	A	`conf`	Backstitch: Counteracting Finite-Sample Bias via Negative Steps. INTERSPEECH Yiming Wang, Vijayaditya Peddinti, Hainan Xu, Xiaohui Zhang, Daniel Povey, Sanjeev Khudanpur
2017	A	`conf`	The Kaldi OpenKWS System: Improving Low Resource Keyword Search. INTERSPEECH Jan Trmal, Matthew Wiesner, Vijayaditya Peddinti, Xiaohui Zhang, Pegah Ghahremani, Yiming Wang, Vimal Manohar, Hainan Xu, Daniel Povey, Sanjeev Khudanpur
2017	A*	`conf`	Zipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora. EMNLP Hainan Xu, Philipp Koehn
2015	A	`conf`	Modeling phonetic context with non-random forests for speech recognition. INTERSPEECH Hainan Xu, Guoguo Chen, Daniel Povey, Sanjeev Khudanpur
2015	A	`conf`	Pronunciation and silence probability modeling for ASR. INTERSPEECH Guoguo Chen, Hainan Xu, Minhua Wu, Daniel Povey, Sanjeev Khudanpur
2013	A	`conf`	Cluster adaptive training with factorized decision trees for speech recognition. INTERSPEECH Kai Yu, Hainan Xu
2012	B	`conf`	Development of the 2012 SJTU HVR system. ICMI Hainan Xu, Yuchen Fan, Kai Yu