Haihua Xu

According to our database1, Haihua Xu authored at least 54 papers between 2008 and 2019.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Other 

Links

On csauthors.net:

Bibliography

2019
Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data.
CoRR, 2019

Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation.
CoRR, 2019

Electromagnetic Transient Modeling and Simulation of Power Converters Based on a Piecewise Generalized State Space Averaging Method.
IEEE Access, 2019

Cross-lingual Voice Conversion with Bilingual Phonetic Posteriorgram and Average Modeling.
Proceedings of the IEEE International Conference on Acoustics, 2019

2018
Re-ranking spoken term detection with acoustic exemplars of keywords.
Speech Communication, 2018

On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition.
CoRR, 2018

Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition.
CoRR, 2018

Average Modeling Approach to Voice Conversion with Non-Parallel Data.
Proceedings of the Odyssey 2018: The Speaker and Language Recognition Workshop, 2018

Mandarin-English Code-switching Speech Recognition.
Proceedings of the Interspeech 2018, 2018

Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition.
Proceedings of the Interspeech 2018, 2018

2017
Mandarin tone modeling using recurrent neural networks.
CoRR, 2017

Pruning Strategies for Partial Search in Spoken Term Detection.
Proceedings of the Eighth International Symposium on Information and Communication Technology, 2017

Improving N-gram language modeling for code-switching speech recognition.
Proceedings of the 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2017

Low-resource spoken keyword search strategies in georgian inspired by distinctive feature theory.
Proceedings of the 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2017

2016
Fantastic 4 system for NIST 2015 Language Recognition Evaluation.
CoRR, 2016

The NNI Vietnamese Speech Recognition System for MediaEval 2016.
Proceedings of the Working Notes Proceedings of the MediaEval 2016 Workshop, 2016

Neural networks based channel compensation for i-vector speaker verification.
Proceedings of the 10th International Symposium on Chinese Spoken Language Processing, 2016

Semi-Supervised and Cross-Lingual Knowledge Transfer Learnings for DNN Hybrid Acoustic Models Under Low-Resource Conditions.
Proceedings of the Interspeech 2016, 2016

Rescoring Hypothesized Detections of Out-of-Vocabulary Keywords Using Subword Samples.
Proceedings of the Interspeech 2016, 2016

Toward High-Performance Language-Independent Query-by-Example Spoken Term Detection for MediaEval 2015: Post-Evaluation Analysis.
Proceedings of the Interspeech 2016, 2016

The 2015 NIST Language Recognition Evaluation: The Shared View of I2R, Fantastic4 and SingaMS.
Proceedings of the Interspeech 2016, 2016

Approximate search of audio queries by using DTW with phone time boundary and data augmentation.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Keyword search using query expansion for graph-based rescoring of hypothesized detections.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Exemplar-inspired strategies for low-resource spoken keyword search in Swahili.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

I-vector based deep neural network acoustic model adaptation using multilingual language resource.
Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2016

2015
Maximum F1-Score Discriminative Training Criterion for Automatic Mispronunciation Detection.
IEEE/ACM Trans. Audio, Speech & Language Processing, 2015

NLP based congestive heart failure case finding: A prospective analysis on statewide electronic medical records.
I. J. Medical Informatics, 2015

The NNI Query-by-Example System for MediaEval 2015.
Proceedings of the Working Notes Proceedings of the MediaEval 2015 Workshop, 2015

A comparative study of BNF and DNN multilingual training on cross-lingual low-resource speech recognition.
Proceedings of the INTERSPEECH 2015, 2015

Spoofing speech detection using high dimensional magnitude and phase features: the NTU approach for ASVspoof 2015 challenge.
Proceedings of the INTERSPEECH 2015, 2015

Multi-softmax deep neural network for semi-supervised training.
Proceedings of the INTERSPEECH 2015, 2015

Language independent query-by-example spoken term detection using N-best phone sequences and partial matching.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Low-resource keyword search strategies for tamil.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

On statistical machine translation method for lexicon refinement in speech recognition.
Proceedings of the IEEE China Summit and International Conference on Signal and Information Processing, 2015

Detecting synthetic speech using long term magnitude and phase information.
Proceedings of the IEEE China Summit and International Conference on Signal and Information Processing, 2015

Risk prediction of stroke: A prospective statewide study on patients in Maine.
Proceedings of the 2015 IEEE International Conference on Bioinformatics and Biomedicine, 2015

On the study of very low-resource language keyword search.
Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2015

Multilingual exemplar-based acoustic model for the NIST Open KWS 2015 evaluation.
Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2015

2014
System and keyword dependent fusion for spoken term detection.
Proceedings of the 2014 IEEE Spoken Language Technology Workshop, 2014

The NNI Query-by-Example System for MediaEval 2014.
Proceedings of the Working Notes Proceedings of the MediaEval 2014 Workshop, 2014

Semi-supervised training for bottle-neck feature based DNN-HMM hybrid systems.
Proceedings of the INTERSPEECH 2014, 2014

Discriminative score normalization for keyword search decision.
Proceedings of the IEEE International Conference on Acoustics, 2014

Strategies for Vietnamese keyword search.
Proceedings of the IEEE International Conference on Acoustics, 2014

Towards better keyword search performance on Malay broadcast news data.
Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2014

2013
The development and analysis of a Malay broadcasr news corpus.
Proceedings of the 2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE), 2013

2011
Aniterative approach to Bayes risk decoding and system combination.
Journal of Zhejiang University - Science C, 2011

Minimum Bayes Risk decoding and system combination based on a recursion for edit distance.
Computer Speech & Language, 2011

2010
An improved consensus-like method for Minimum Bayes Risk decoding and lattice combination.
Proceedings of the IEEE International Conference on Acoustics, 2010

2009
Minimum tag error for discriminative training of conditional random fields.
Inf. Sci., 2009

Minimum hypothesis phone error as a decoding method for speech recognition.
Proceedings of the INTERSPEECH 2009, 2009

An efficient multistage Rover method for Automatic Speech recognition.
Proceedings of the 2009 IEEE International Conference on Multimedia and Expo, 2009

Minimum phone error based stream weight training for mandarin audio-visual Speech recognition.
Proceedings of the 2009 IEEE International Conference on Multimedia and Expo, 2009

A hybrid visual feature extraction method for audio-visual speech recognition.
Proceedings of the International Conference on Image Processing, 2009

2008
Towards more efficient and accurate methods for Mandarin LVCSR discriminative training.
Proceedings of the 2008 IEEE International Conference on Multimedia and Expo, 2008


  Loading...