Haihua Xu

发表

Aniterative approach to Bayes risk decoding and system combination

Haihua Xu, Jie Zhu, 2011, Journal of Zhejiang University SCIENCE C.

On statistical machine translation method for lexicon refinement in speech recognition

Haizhou Li, Chng Eng Siong, Xiong Xiao, 2015, 2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP).

Audio Codec Simulation based Data Augmentation for Telephony Speech Recognition

Chng Eng Siong, Haihua Xu, Thi-Ly Vu, 2019, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

The NNI Vietnamese Speech Recognition System for MediaEval 2016

Bin Ma, Haizhou Li, Chng Eng Siong, 2016, MediaEval.

Pruning Strategies for Partial Search in Spoken Term Detection

Chng Eng Siong, Xiong Xiao, Haihua Xu, 2017, SoICT.

Language independent query-by-example spoken term detection using N-best phone sequences and partial matching

Bin Ma, Haizhou Li, Chng Eng Siong, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The NTU-AISG Text-to-speech System for Blizzard Challenge 2020 pdf

Haihua Xu, Haobo Zhang, Hao Huang, 2020, ArXiv.

Application On the Accidental Vehicle Technology Expertise and Software Development

Haihua Xu, Guangfu Li, 2015 .

NLP based congestive heart failure case finding: A prospective analysis on statewide electronic medical records

Haihua Xu, Rui Liu, Yue Wang, 2015, Int. J. Medical Informatics.

Enriching Under-Represented Named-Entities To Improve Speech Recognition Performance pdf

Chng Eng Siong, Haihua Xu, Yerbolat Khassanov, 2020, ArXiv.

Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems pdf

Chng Eng Siong, Haihua Xu, Hao Huang, 2020, ArXiv.

Detecting synthetic speech using long term magnitude and phase information

Haizhou Li, Chng Eng Siong, Xiong Xiao, 2015, 2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP).

Minimum tag error for discriminative training of conditional random fields

Haihua Xu, Hao Huang, Ying Xiong, 2009, Inf. Sci..

The NNI Query-by-Example System for MediaEval 2015

Chng Eng Siong, Haihua Xu, Haizhou Li, 2014, MediaEval.

Toward High-Performance Language-Independent Query-by-Example Spoken Term Detection for MediaEval 2015: Post-Evaluation Analysis

Bin Ma, Haizhou Li, Chng Eng Siong, 2016, INTERSPEECH.

A Flexibility Planning Methodfor Hybrid AC / DC Distribution Network

Haihua Xu, Hui Cai, Weimin Xi, 2018, 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2).

An efficient multistage Rover method for Automatic Speech recognition

Haihua Xu, Jie Zhu, Guanyong Wu, 2009, 2009 IEEE International Conference on Multimedia and Expo.

Minimum hypothesis phone error as a decoding method for speech recognition

Haihua Xu, Jie Zhu, Daniel Povey, 2009, INTERSPEECH.

Strategies for Vietnamese keyword search

Bin Ma, Haizhou Li, Haihua Xu, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Electromagnetic Transient Modeling and Simulation of Power Converters Based on a Piecewise Generalized State Space Averaging Method

Haihua Xu, Xiaolong Wu, Lei Wang, 2019, IEEE Access.

Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data pdf

Bin Ma, Chng Eng Siong, Haihua Xu, 2019, INTERSPEECH.

On the study of very low-resource language keyword search

Haizhou Li, Chng Eng Siong, Tze Yuang Chong, 2015, 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

Improving N-gram language modeling for code-switching speech recognition

Haizhou Li, Chng Eng Siong, Tze Yuang Chong, 2017, 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Low-resource spoken keyword search strategies in georgian inspired by distinctive feature theory

Chng Eng Siong, Haihua Xu, Haizhou Li, 2017, 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Spoofing speech detection using high dimensional magnitude and phase features: the NTU approach for ASVspoof 2015 challenge

Haizhou Li, Chng Eng Siong, Xiong Xiao, 2015, INTERSPEECH.

Exemplar-inspired strategies for low-resource spoken keyword search in Swahili

Bin Ma, Haizhou Li, Chng Eng Siong, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Semi-supervised training for bottle-neck feature based DNN-HMM hybrid systems

Haizhou Li, Chng Eng Siong, Haihua Xu, 2014, INTERSPEECH.

Discriminative score normalization for keyword search decision

Haizhou Li, Chng Eng Siong, Haihua Xu, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Towards better keyword search performance on Malay broadcast news data

Haizhou Li, Chng Eng Siong, Haihua Xu, 2014, Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific.

Average Modeling Approach to Voice Conversion with Non-Parallel Data

Haizhou Li, Chng Eng Siong, Haihua Xu, 2018, Odyssey.

Spatial-Scale Aligned Network for Fine-Grained Recognition pdf

Haihua Xu, Yu-Wing Tai, Chong Sun, 2020, ArXiv.

On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition

Haizhou Li, Chng Eng Siong, Haihua Xu, 2018, INTERSPEECH.

Independent Language Modeling Architecture for End-To-End ASR

Chng Eng Siong, Haihua Xu, Haizhou Li, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving code-switching speech recognition with data augmentation and system combination

Chng Eng Siong, Haihua Xu, Duo Ma, 2019, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation

Chng Eng Siong, Haihua Xu, Yerbolat Khassanov, 2019, INTERSPEECH.

Neural networks based channel compensation for i-vector speaker verification

Haizhou Li, Chng Eng Siong, Xiong Xiao, 2016, 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Low-resource keyword search strategies for tamil

Bin Ma, Haizhou Li, Chng Eng Siong, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

System and keyword dependent fusion for spoken term detection

Haizhou Li, Chng Eng Siong, Haihua Xu, 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning pdf

Chng Eng Siong, Haihua Xu, Chongjia Ni, 2020, ArXiv.

Multilingual exemplar-based acoustic model for the NIST Open KWS 2015 evaluation

Haizhou Li, Chng Eng Siong, Xiong Xiao, 2015, 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

The 2015 NIST Language Recognition Evaluation: The Shared View of I2R, Fantastic4 and SingaMS

Bin Ma, Haizhou Li, Chng Eng Siong, 2016, INTERSPEECH.

A multilingual approach to joint Speech and Accent Recognition with DNN-HMM framework pdf

Chng Eng Siong, Haihua Xu, Haobo Zhang, 2020, ArXiv.

Risk prediction of stroke: A prospective statewide study on patients in Maine

Haihua Xu, Yue Wang, Hua Jin, 2015, 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

Keyword search using query expansion for graph-based rescoring of hypothesized detections

Haizhou Li, Chng Eng Siong, Xiong Xiao, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Mandarin-English Code-switching Speech Recognition

Haizhou Li, Chng Eng Siong, Haihua Xu, 2018, INTERSPEECH.

Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-Switching Speech Recognition

Chng Eng Siong, Haihua Xu, Hao Huang, 2020, INTERSPEECH.

I-vector based deep neural network acoustic model adaptation using multilingual language resource

Haizhou Li, Chng Eng Siong, Xiong Xiao, 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

Minimum phone error based stream weight training for mandarin audio-visual Speech recognition

Haihua Xu, Jie Zhu, Guanyong Wu, 2009, 2009 IEEE International Conference on Multimedia and Expo.

Simulation on the self-compacting concrete by an enhanced Lagrangian particle method

Haihua Xu, Jun Wu, Xuemei Liu, 2016 .

Fantastic 4 system for NIST 2015 Language Recognition Evaluation pdf

Bin Ma, Haizhou Li, Xiong Xiao, 2016, ArXiv.

A comparative study of BNF and DNN multilingual training on cross-lingual low-resource speech recognition

Chng Eng Siong, Xiong Xiao, Haihua Xu, 2015, INTERSPEECH.

Maximum F1-Score Discriminative Training Criterion for Automatic Mispronunciation Detection

Haihua Xu, Hao Huang, Xianhui Wang, 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Minimum Bayes Risk decoding and system combination based on a recursion for edit distance

Haihua Xu, Daniel Povey, Jie Zhu, 2011, Comput. Speech Lang..

Towards more efficient and accurate methods for Mandarin LVCSR discriminative training

Haihua Xu, Jie Zhu, 2008, 2008 IEEE International Conference on Multimedia and Expo.

Mandarin tone modeling using recurrent neural networks pdf

Haihua Xu, Hao Huang, Ying Hu, 2017, ArXiv.

A hybrid visual feature extraction method for audio-visual speech recognition

Haihua Xu, Jie Zhu, Guanyong Wu, 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

Multi-softmax deep neural network for semi-supervised training

Haihua Xu, Hang Su, Hang Su, 2015, INTERSPEECH.

Re-ranking spoken term detection with acoustic exemplars of keywords

Haizhou Li, Chng Eng Siong, Xiong Xiao, 2018, Speech Commun..

Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition

Chng Eng Siong, Haihua Xu, Lei Xie, 2018, INTERSPEECH.

Semi-Supervised and Cross-Lingual Knowledge Transfer Learnings for DNN Hybrid Acoustic Models Under Low-Resource Conditions

Haizhou Li, Chng Eng Siong, Xiong Xiao, 2016, INTERSPEECH.

Cross-lingual Voice Conversion with Bilingual Phonetic Posteriorgram and Average Modeling

Haizhou Li, Haihua Xu, Xiaohai Tian, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Rescoring Hypothesized Detections of Out-of-Vocabulary Keywords Using Subword Samples

Haizhou Li, Chng Eng Siong, Xiong Xiao, 2016, INTERSPEECH.

Approximate search of audio queries by using DTW with phone time boundary and data augmentation

Bin Ma, Haizhou Li, Chng Eng Siong, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

長崎唐通事何礼之の英語習得[含何礼之履歴]

Haihua Xu, 許海華, 2011 .

An improved consensus-like method for Minimum Bayes Risk decoding and lattice combination

Haihua Xu, Jie Zhu, Daniel Povey, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

A transfer learning approach to goodness of pronunciation based automatic mispronunciation detection.

Haihua Xu, Hao Huang, Ying Hu, 2017, The Journal of the Acoustical Society of America.

E2E-Based Multi-Task Learning Approach to Joint Speech and Accent Recognition

Chng Eng Siong, Haihua Xu, Eng Siong Chng, 2021, Interspeech.

Multitask-based joint learning approach to robust ASR for radio communication speech pdf

Chng Eng Siong, Haihua Xu, Van Tung Pham, 2021, 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Minimum word error training for non-autoregressive Transformer-based code-switching ASR

Haihua Xu, Eng Siong Chng, Yizhou Peng, 2021 .