Wangd-wiki-bib
来自cslt Wiki
journal
@article{tang2018phonetic,
title={Phonetic temporal neural model for language identification},
author={Tang, Zhiyuan and Wang, Dong and Chen, Yixiang and Li, Lantian and Abel, Andrew},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
volume={26},
number={1},
pages={134--144},
year={2018},
publisher={IEEE}
}
@article{tang2017collaborative,
title={Collaborative joint training with multitask recurrent model for speech and speaker recognition},
author={Tang, Zhiyuan and Li, Lantian and Wang, Dong and Vipperla, Ravichander},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
volume={25},
number={3},
pages={493--504},
year={2017},
publisher={IEEE}
}
@article{ma2016similar,
title={Similar Word Model for Unfrequent Word Enhancement in Speech Recognition},
author={Ma, Xi and Wang, Dong and Tejedor, Javier and Ma, Xi and Wang, Dong and Tejedor, Javier and Tejedor, Javier and Ma, Xi and Wang,
Dong},
journal={IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)},
volume={24},
number={10},
pages={1819--1830},
year={2016},
publisher={IEEE Press}
}
@article{li2016improving,
title={Improving short utterance speaker recognition by modeling speech unit classes},
author={Li, Lantian and Wang, Dong and Zhang, Chenhao and Zheng, Thomas Fang},
journal={IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)},
volume={24},
number={6},
pages={1129--1139},
year={2016},
publisher={IEEE Press}
}
@article{bie2015detection,
title={Detection and reconstruction of clipped speech for speaker recognition},
author={Bie, Fanhu and Wang, Dong and Wang, Jun and Zheng, Thomas Fang},
journal={Speech Communication},
volume={72},
pages={218--231},
year={2015},
publisher={Elsevier}
}
@article{yin2015noisy,
title={Noisy training for deep neural networks in speech recognition},
author={Yin, Shi and Liu, Chao and Zhang, Zhiyong and Lin, Yiye and Wang, Dong and Tejedor, Javier and Zheng, Thomas Fang and Li, Yinguo},
journal={EURASIP Journal on Audio, Speech, and Music Processing},
volume={2015},
number={1},
pages={2},
year={2015},
publisher={Springer}
}
@article{tejedor2014feature,
title={Feature analysis for discriminative confidence estimation in spoken term detection},
author={Tejedor, Javier and Toledano, Doroteo T and Wang, Dong and King, Simon and Col{\'a}s, Jos{\'e}},
journal={Computer Speech \& Language},
volume={28},
number={5},
pages={1083--1114},
year={2014},
publisher={Elsevier}
}
@article{wang2013online,
title={Online non-negative convolutive pattern learning for speech signals},
author={Wang, Dong and Vipperla, Ravichander and Evans, Nicholas and Zheng, Thomas Fang},
journal={IEEE Transactions on Signal Processing},
volume={61},
number={1},
pages={44--56},
year={2013},
publisher={IEEE}
}
@article{wang2012direct,
title={Direct posterior confidence for out-of-vocabulary spoken term detection},
author={Wang, Dong and King, Simon and Frankel, Joe and Vipperla, Ravichander and Evans, Nicholas and Troncy, Rapha{\"e}l},
journal={ACM Transactions on Information Systems (TOIS)},
volume={30},
number={3},
pages={16},
year={2012},
publisher={ACM}
}
@article{wang2012term,
title={Term-dependent confidence normalisation for out-of-vocabulary spoken term detection},
author={Wang, Dong and Tejedor, Javier and King, Simon and Frankel, Joe},
journal={Journal of Computer Science and Technology},
volume={27},
number={2},
pages={358--375},
year={2012},
publisher={Springer}
}
@article{evans2012comparative,
title={A comparative study of bottom-up and top-down approaches to speaker diarization},
author={Evans, Nicholas and Bozonnet, Simon and Wang, Dong and Fredouille, Corinne and Troncy, Rapha{\"e}l},
journal={IEEE Transactions on Audio, speech, and language processing},
volume={20},
number={2},
pages={382--392},
year={2012},
publisher={IEEE}
}
@article{tejedor2013evolutionary,
title={Evolutionary discriminative confidence estimation for spoken term detection},
author={Tejedor, Javier and Echeverr{\'\i}a, Alejandro and Wang, Dong and Vipperla, Ravichander},
journal={Multimedia tools and applications},
volume={62},
number={1},
pages={5--34},
year={2013},
publisher={Springer}
}
@article{wang2011sound,
title={to-sound pronunciation prediction using conditional random fields},
author={Wang, Dong and King, Simon},
journal={IEEE Signal Processing Letters},
volume={18},
number={2},
pages={122--125},
year={2011},
publisher={IEEE}
}
@article{wang2011stochastic,
title={Stochastic pronunciation modeling for out-of-vocabulary spoken term detection},
author={Wang, Dong and King, Simon and Frankel, Joe},
journal={IEEE Transactions on Audio, Speech, and Language Processing},
volume={19},
number={4},
pages={688--698},
year={2011},
publisher={IEEE}
}
@article{tejedor2008comparison,
title={A comparison of grapheme and phoneme-based units for Spanish spoken term detection},
author={Tejedor, Javier and Wang, Dong and Frankel, Joe and King, Simon and Col{\'a}s, Jos{\'e}},
journal={Speech Communication},
volume={50},
number={11-12},
pages={980--991},
year={2008},
publisher={Elsevier}
}
conference
@inproceedings{li2017full,
title={Full-info Training for Deep Speaker Feature Learning},
author={Li, Lantian and Tang, Zhiyuan and Wang, Dong},
booktitle={ICASSP 2018},
year={2018}
}
@inproceedings{zhang2017human,
title={Human and Machine Speaker Recognition Based on Short Trivial Events},
author={Zhang, Miao and Kang, Xiaofei and Wang, Yanqing and Li, Lantian and Tang, Zhiyuan and Dai, Haisheng and Wang, Dong},
booktitle={ICASSP 2018},
year={2017}
}
@inproceedings{wang2017deep,
title={Deep factorization for speech signal},
author={Wang, Dong and Li, Lantian and Shi, Ying and Chen, Yixiang and Tang, Zhiyuan},
booktitle={ICASSP 2018},
year={2018}
}
@inproceedings{li2017collaborative,
title={Collaborative Learning for Language and Speaker Recognition},
author={Li, Lantian and Tang, Zhiyuan and Wang, Dong and Abel, Andrew and Feng, Yang and Zhang, Shiyue},
booktitle={National Conference on Man-Machine Speech Communication},
pages={58--69},
year={2017},
organization={Springer}
}
@inproceedings{tang2017ap17,
title={Ap17-olr challenge: Data, plan, and baseline},
author={Tang, Zhiyuan and Wang, Dong and Chen, Yixiang and Chen, Qing},
booktitle={Proceedings of APSIPA Annual Summit and Conference},
year={2017}
}
@inproceedings{zhang2017memory,
title={Memory-augmented Chinese-Uyghur Neural Machine Translation},
author={Zhang, Shiyue and Mahmut, Gulnigar and Wang, Dong and Hamdulla, Askar},
journal={arXiv preprint arXiv:1706.08683},
booktitle={Proceedings of APSIPA Annual Summit and Conference},
year={2017}
}
@inproceedings{shi2017free,
title={A Free Kazakh Speech Database and a Speech Recognition Baseline},
author={Shi, Ying and Hamdulla, Askar and Tang, Zhiyuan and Wang, Dong and Zheng, Thomas Fang},
booktitle={Proceedings of APSIPA Annual Summit and Conference},
volume={2017},
pages={12--15},
year={2017}
@inproceedings{li2017enhanced,
title={Enhanced Neural Machine Translation by Learning from Draft},
author={Li, Aodong and Zhang, Shiyue and Wang, Dong and Zheng, Thomas Fang},
booktitle={APSIPA2017},
year={2017}
}
@inproceedings{li2017cross,
title={Cross-lingual speaker verification with deep feature learning},
author={Li, Lantian and Wang, Dong and Rozi, Askar and Zheng, Thomas Fang},
booktitle={APSIPA2017},
year={2017}
}
@inproceedings{wang2017deep,
title={Deep speaker verification: Do we need end to end?},
author={Wang, Dong and Li, Lantian and Tang, Zhiyuan and Zheng, Thomas Fang},
booktitle={APSIPA2017},
year={2017}
}
@inproceedings{zhang2017speaker,
title={Speaker Recognition with Cough, Laugh and" Wei"},
author={Zhang, Miao and Chen, Yixiang and Li, Lantian and Wang, Dong},
booktitle={APSIPA2017},
year={2017}
}
@inproceedings{wang2017m2asr,
title={M2ASR: Ambitions and First year Progress},
author={ Dong Wang and Thomas Zheng and Zhiyuan Tang and Ying Shi and Lantian Li and Shiyue Zhang and Hongzhi Yu and
Guanyu Li and Shipeng Xu and Askar Hamdulla and Mijit Ablimit and Gulnigar Mahmut,},
booktitle={OCOCOSDA-2017},
year={2017}
}
@inproceedings{tang2017phone,
title={Phone-aware Neural Language Identification},
author={Tang, Zhiyuan and Wang, Dong and Chen, Yixiang and Shi, Ying and Li, Lantian},
booktitle={OCOCOSDA-2017},
year={2017}
}
@inproceedings{feng2017memory,
title={Memory-augmented neural machine translation},
author={Feng, Yang and Zhang, Shiyue and Zhang, Andi and Wang, Dong and Abel, Andrew},
booktitle={EMNLP 2017},
year={2017}
}
@inproceedings{li2017study,
title={A Study on Replay Attack and Anti-Spoofing for Automatic Speaker Verification},
author={Li, Lantian and Chen, Yixiang and Wang, Dong and Zheng, Thomas Fang},
booktitle={Interspeech 2017},
year={2017}
@inproceedings{li2017deep,
title={Deep speaker feature learning for text-independent speaker verification},
author={Li, Lantian and Chen, Yixiang and Shi, Ying and Tang, Zhiyuan and Wang, Dong},
booktitle={Interspeech 2017},
year={2017}
}
@inproceedings{zhang2017flexible,
title={Flexible and creative chinese poetry generation using neural memory},
author={Zhang, Jiyuan and Feng, Yang and Wang, Dong and Wang, Yang and Abel, Andrew and Zhang, Shiyue and Zhang, Andi},
booktitle={ACL 2017},
year={2017}
}
@inproceedings{tang2017memory,
title={Memory visualization for gated recurrent neural networks in speech recognition},
author={Tang, Zhiyuan and Shi, Ying and Wang, Dong and Feng, Yang and Zhang, Shiyue},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2017 IEEE International Conference on},
pages={2736--2740},
year={2017},
organization={IEEE}
}
@incollection{zhang2016relation,
title={Relation Classification: CNN or RNN?},
author={Zhang, Dongxu and Wang, Dong},
booktitle={Natural Language Understanding and Intelligent Applications},
pages={665--675},
year={2016},
publisher={Springer}
}
@incollection{zhang2016learning,
title={Learning from LDA using deep neural networks},
author={Zhang, Dongxu and Luo, Tianyi and Wang, Dong},
booktitle={Natural Language Understanding and Intelligent Applications},
pages={657--664},
year={2016},
publisher={Springer}
}
@inproceedings{rozi2016language,
title={Language-aware PLDA for multilingual speaker recognition},
author={Rozi, Askar and Wang, Dong and Li, Lantian and Zheng, Thomas Fang},
booktitle={Coordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA), 2016 Conference of The Oriental
Chapter of International Committee for},
pages={161--165},
year={2016},
organization={IEEE}
}
@inproceedings{wang2016oc16,
title={OC16-CE80: A Chinese-English mixlingual database and a speech recognition baseline},
author={Wang, Dong and Tang, Zhiyuan and Tang, Difei and Chen, Qing},
booktitle={Coordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA), 2016 Conference of The Oriental
Chapter of International Committee for},
pages={84--88},
year={2016},
organization={IEEE}
}
@inproceedings{zhao2016local,
title={Local training for PLDA in speaker verification},
author={Zhao, Chenghui and Li, Lantian and Wang, Dong and Pu, April},
booktitle={Coordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA), 2016 Conference of The Oriental
Chapter of International Committee for},
pages={156--160},
year={2016},
organization={IEEE}
}
@inproceedings{li2016max,
title={Max-margin metric learning for speaker recognition},
author={Li, Lantian and Wang, Dong and Xing, Chao and Zheng, Thomas Fang},
booktitle={Chinese Spoken Language Processing (ISCSLP), 2016 10th International Symposium on},
pages={1--4},
year={2016},
organization={IEEE}
}
@inproceedings{li2016binary,
title={Binary speaker embedding},
author={Li, Lantian and Xing, Chao and Wang, Dong and Yu, Kaimin and Zheng, Thomas Fang},
booktitle={Chinese Spoken Language Processing (ISCSLP), 2016 10th International Symposium on},
pages={1--4},
year={2016},
organization={IEEE}
}
@inproceedings{li2016system,
title={System combination for short utterance speaker recognition},
author={Li, Lantian and Wang, Dong and Zhang, Xiaodong and Zheng, Thomas Fang and Jin, Panshi},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2016 Asia-Pacific},
pages={1--5},
year={2016},
organization={IEEE}
}
@inproceedings{tang2016multi,
title={Multi-task recurrent model for speech and speaker recognition},
author={Tang, Zhiyuan and Li, Lantian and Wang, Dong},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2016 Asia-Pacific},
pages={1--4},
year={2016},
organization={IEEE}
}
@inproceedings{rozi2016feature,
title={Feature transformation for speaker verification under speaking rate mismatch condition},
author={Rozi, Askar and Li, Lantian and Wang, Dong and Zheng, Thomas Fang},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2016 Asia-Pacific},
pages={1--4},
year={2016},
organization={IEEE}
}
@inproceedings{liu2016learning,
title={Learning ordered word representations with $\gamma$-decay dropout},
author={Liu, Aiting and Xing, Chao and Feng, Yang and Wang, Dong},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2016 Asia-Pacific},
pages={1--5},
year={2016},
organization={IEEE}
}
@inproceedings{wang2016ap16,
title={Ap16-ol7: A multilingual database for oriental languages and a language recognition baseline},
author={Wang, Dong and Li, Lantian and Tang, Difei and Chen, Qing},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2016 Asia-Pacific},
pages={1--5},
year={2016},
organization={IEEE}
}
@inproceedings{tang2016multi,
title={Multi-task recurrent model for true multilingual speech recognition},
author={Zhiyuan Tang and Lantian Li and Dong Wang},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2016 Asia-Pacific},
pages={1--5},
year={2016},
organization={IEEE}
}
@inproceedings{wang2016can,
title={Can machine generate traditional Chinese poetry? a feigenbaum test},
author={Wang, Qixin and Luo, Tianyi and Wang, Dong},
booktitle={International Conference on Brain Inspired Cognitive Systems},
pages={34--46},
year={2016},
organization={Springer}
}
@inproceedings{wang2016deep,
title={Deep and sparse learning in speech and language processing: An overview},
author={Wang, Dong and Zhou, Qiang and Hussain, Amir},
booktitle={International Conference on Brain Inspired Cognitive Systems},
pages={171--183},
year={2016},
organization={Springer}
}
@inproceedings{wang2016chinese,
title={Chinese song iambics generation with neural attention-based model},
author={Wang, Qixin and Luo, Tianyi and Wang, Dong and Xing, Chao},
journal={IJCAI 2016},
year={2016}
}
@inproceedings{wang2016vmf,
title={VMF-SNE: Embedding for spherical data},
author={Wang, Mian and Wang, Dong},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on},
pages={2344--2348},
year={2016},
organization={IEEE}
}
@inproceedings{tang2016recurrent,
title={Recurrent neural network training with dark knowledge transfer},
author={Tang, Zhiyuan and Wang, Dong and Zhang, Zhiyong},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on},
pages={5900--5904},
year={2016},
organization={IEEE}
}
@inproceedings{li2015improved,
title={Improved deep speaker feature learning for text-dependent speaker recognition},
author={Li, Lantian and Lin, Yiye and Zhang, Zhiyong and Wang, Dong},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2015 Asia-Pacific},
pages={426--429},
year={2015},
organization={IEEE}
}
@inproceedings{zhao2015music,
title={Music removal by convolutional denoising autoencoder in speech recognition},
author={Zhao, Mengyuan and Wang, Dong and Zhang, Zhiyong and Zhang, Xuewei},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2015 Asia-Pacific},
pages={338--341},
year={2015},
organization={IEEE}
}
@inproceedings{pan2015document,
title={Document classification with spherical word vectors},
author={Pan, Yiqiao and Xing, Chao and Wang, Dong},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2015 Asia-Pacific},
pages={270--273},
year={2015},
organization={IEEE}
}
@inproceedings{wang2015transfer,
title={Transfer learning for speech and language processing},
author={Wang, Dong and Zheng, Thomas Fang},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2015 Asia-Pacific},
pages={1225--1237},
year={2015},
organization={IEEE}
}
@inproceedings{luo2015stochastic,
title={Stochastic top-k listnet},
={Luo, Tianyi and Wang, Dong and Liu, Rong and Pan, Yiqiao},
booktitle={EMNLP2015},
year={2015}
}
@inproceedings{rozi2015open,
title={An open/free database and Benchmark for Uyghur speaker recognition},
author={Rozi, Askar and Wang, Dong and Zhang, Zhiyong and Zheng, Thomas Fang},
booktitle={Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE), 2015
International Conference},
pages={81--85},
year={2015},
organization={IEEE}
}
@article{rouzi2017thuyg,
title={THUYG-20: A free Uyghur speech database},
author={Rouzi, Aisikaer and Shi, YIN and Zhiyong, ZHANG and Dong, WANG and Hamdulla, Askar and Fang, ZHENG},
journal={Journal of Tsinghua University (Science and Technology)},
volume={57},
number={2},
pages={182--187},
year={2017}
}
@inproceedings{ma2015recognize,
title={Recognize foreign low-frequency words with similar pairs},
author={Ma, Xi and Wang, Xiaoxi and Wang, Dong and Zhang, Zhiyong},
booktitle={Interspeech 2015},
year={2015}
}
@inproceedings{zeng2015learning,
title={Learning speech rate in speech recognition},
author={Zeng, Xiangyu and Yin, Shi and Wang, Dong},
booktitle={Interspeech 2015},
year={2015}
}
@inproceedings{zhang2015joint,
title={Joint semantic relevance learning with text data and graph knowledge},
author={Zhang, Dongxu and Yuan, Bin and Wang, Dong and Liu, Rong},
booktitle={Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality},
pages={32--40},
year={2015}
}
@inproceedings{ma2015low,
title={Low-frequency word enhancement with similar pairs in speech recognition},
author={Ma, Xi and Wang, Xiaoxi and Wang, Dong},
booktitle={Signal and Information Processing (ChinaSIP), 2015 IEEE China Summit and International Conference on},
pages={343--347},
year={2015},
organization={IEEE}
}
@inproceedings{askar2015cross,
title={Cross-lingual speaker verification based on linear transform},
author={Askar, Rozi and Wang, Dong and Bie, Fanhu and Wang, Jun and Zheng, Thomas Fang},
booktitle={Signal and Information Processing (ChinaSIP), 2015 IEEE China Summit and International Conference on},
pages={519--523},
year={2015},
organization={IEEE}
}
@inproceedings{xing2015normalized,
title={Normalized word embedding and orthogonal transform for bilingual word translation},
author={Xing, Chao and Wang, Dong and Liu, Chao and Lin, Yiye},
booktitle={Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
pages={1006--1011},
year={2015}
}
@inproceedings{zhang2015lasso,
title={Lasso-based reverberation suppression in automatic speech recognition},
author={Zhang, Xuewei and Lin, Yiye and Wang, Dong},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on},
pages={5034--5037},
year={2015},
organization={IEEE}
}
@inproceedings{wang2014discriminative,
title={Discriminative scoring for speaker recognition based on i-vectors},
author={Wang, Jun and Wang, Dong and Zhu, Ziwei and Zheng, Thomas Fang and Soong, Frank},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific},
pages={1--5},
year={2014},
organization={IEEE}
}
@inproceedings{xing2014document,
title={Document classification with distributions of word vectors},
author={Xing, Chao and Wang, Dong and Zhang, Xuewei and Liu, Chao},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific},
pages={1--5},
year={2014},
organization={IEEE}
}
@incollection{tejedor2014atvs,
title={ATVS-CSLT-HCTLab System for NIST 2013 Open Keyword Search Evaluation},
author={Tejedor, Javier and Toledano, Doroteo T and Wang, Dong},
booktitle={Advances in Speech and Language Technologies for Iberian Languages},
pages={249--258},
year={2014},
publisher={Springer}
}
@inproceedings{wang2014research,
title={Research on generalization property of time-varying Fbank-weighted MFCC for i-vector based speaker verification},
author={Wang, Jun and Li, Lantian and Wang, Dong and Zheng, Thomas Fang},
booktitle={Chinese Spoken Language Processing (ISCSLP), 2014 9th International Symposium on},
pages={423--423},
year={2014},
organization={IEEE}
}
@inproceedings{bie2014research,
title={Research on truncated speech in speaker verification},
author={Bie, Fanhu and Wang, Dong and Zheng, Thomas Fang},
booktitle={Chinese Spoken Language Processing (ISCSLP), 2014 9th International Symposium on},
pages={425--425},
year={2014},
organization={IEEE}
}
@inproceedings{liu2014document,
title={Document classification based on word vectors},
author={Liu, Rong and Wang, Dong and Xing, Chao},
booktitle={ISCSLP'14},
year={2014}
}
@inproceedings{liu2014pruning,
title={Pruning deep neural networks by optimal brain damage},
author={Liu, Chao and Zhang, Zhiyong and Wang, Dong},
booktitle={Fifteenth Annual Conference of the International Speech Communication Association},
year={2014}
}
@inproceedings{bie2014block,
title={Block-wise training for i-vector},
author={Bie, Fanhu and Wang, Jun and Wang, Dong and Zheng, Thomas Fang},
booktitle={Signal and Information Processing (ChinaSIP), 2014 IEEE China Summit \& International Conference on},
pages={11--15},
year={2014},
organization={IEEE}
}
@inproceedings{bie2013emotional,
title={Emotional speaker verification with linear adaptation},
author={Bie, Fanhu and Wang, Dong and Zheng, Thomas Fang and Chen, Ruxin},
booktitle={Signal and Information Processing (ChinaSIP), 2013 IEEE China Summit \& International Conference on},
pages={91--94},
year={2013},
organization={IEEE}
}
@inproceedings{meng2014noisy,
title={Noisy training for deep neural networks},
author={Meng, Xiangtao and Liu, Chao and Zhang, Zhiyong and Wang, Dong},
booktitle={Signal and Information Processing (ChinaSIP), 2014 IEEE China Summit \& International Conference on},
pages={16--20},
year={2014},
organization={IEEE}
}
@inproceedings{bie2013emotional,
title={Emotional adaptive training for speaker verification},
author={Bie, Fanhu and Wang, Dong and Zheng, Thomas Fang and Tejedor, Javier and Chen, Ruxin},
booktitle={Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2013 Asia-Pacific},
pages={1--4},
year={2013},
organization={IEEE}
}
@inproceedings{wang2013sequential,
title={Sequential model adaptation for speaker verification},
author={Wang, Jun and Wang, Dong and Wu, Xiaojun and Fang Zheng, Thomas and Tejedor Noguerales, Javier},
booktitle={Interspeech},
year={2013},
organization={International Speech Communication Association}
}
@inproceedings{qi2013bottleneck,
title={Bottleneck features based on gammatone frequency cepstral coefficients},
author={Qi, Jun and Wang, Dong and Xu, Ji and Tejedor Noguerales, Javier},
booktitle={Interspeech},
year={2013},
organization={International Speech Communication Association}
}
@inproceedings{qi2013subspace,
title={Subspace models for bottleneck features},
author={Qi, Jun and Wang, Dong and Tejedor Noguerales, Javier},
booktitle={Interspeech},
year={2013},
organization={International Speech Communication Association}
}
@inproceedings{wang2013sequential,
title={Sequential UBM adaptation for speaker verification},
author={Wang, Jun and Wang, Dong and Wu, Xiaojun and Zheng, Thomas Fang},
booktitle={Signal and Information Processing (ChinaSIP), 2013 IEEE China Summit \& International Conference on},
pages={356--359},
year={2013},
organization={IEEE}
}
@inproceedings{bie2013emotional,
title={Emotional speaker verification with linear adaptation},
author={Bie, Fanhu and Wang, Dong and Zheng, Thomas Fang and Chen, Ruxin},
booktitle={Signal and Information Processing (ChinaSIP), 2013 IEEE China Summit \& International Conference on},
pages={91--94},
year={2013},
organization={IEEE}
}
@inproceedings{qi2013auditory,
title={Auditory features based on gammatone filters for robust speech recognition},
author={Qi, Jun and Wang, Dong and Jiang, Yi and Liu, Runsheng},
booktitle={Circuits and Systems (ISCAS), 2013 IEEE International Symposium on},
pages={305--308},
year={2013},
organization={IEEE}
}
@inproceedings{wang2012heterogeneous,
title={Heterogeneous convolutive non-negative sparse coding},
author={Wang, Dong and Tejedor Noguerales, Javier},
booktitle={Interspeech},
year={2012},
organization={International Speech Communication Association}
}
@inproceedings{liu2012n,
title={N-gram FST indexing for spoken term detection},
author={Liu, Chao and Wang, Dong and Tejedor Noguerales, Javier},
booktitle={Interspeech},
year={2012},
organization={International Speech Communication Association}
}
@inproceedings{vipperla2012speech,
title={Speech overlap detection and attribution using convolutive non-negative sparse coding},
author={Vipperla, Ravichander and Geiger, J{\"u}rgen T and Bozonnet, Simon and Wang, Dong and Evans, Nicholas and Schuller, Bj{\"o}rn and Rigoll, Gerhard},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on},
pages={4181--4184},
year={2012},
organization={IEEE}
}
@inproceedings{wang2011parallel,
title={Parallel and hierarchical decision making for sparse coding in speech recognition},
author={Wang, Dong and Vipperla, Ravichander and Evans, Nicholas},
booktitle={Twelfth Annual Conference of the International Speech Communication Association},
year={2011}
}
@inproceedings{wang2011online,
title={Online pattern learning for convolutive non-negative sparse coding},
author={Wang, D and Vipperla, R and Evans, N},
year={2011},
organization={Interspeech}
}
@inproceedings{bozonnet2011linguistic,
title={Linguistic influences on bottom-up and top-down clustering for speaker diarization},
author={Bozonnet, Simon and Wang, Dong and Evans, Nicholas and Troncy, Rapha{\"e}l},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on},
pages={4424--4427},
year={2011},
organization={IEEE}
}
@inproceedings{vipperla2011robust,
title={Robust speech recognition in multi-source noise environments using convolutive non-negative matrix factorization},
author={Vipperla, Ravichander and Bozonnet, Simon and Wang, Dong and Evans, Nicholas},
booktitle={Machine Listening in Multisource Environments},
year={2011}
}
@inproceedings{wang2011handling,
title={Handling overlaps in spoken term detection},
author={Wang, Dong and Evans, Nicholas and Troncy, Rapha{\"e}l and King, Simon},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on},
pages={5656--5659},
year={2011},
organization={IEEE}
}
@inproceedings{tejedor2011evolutionary,
title={An evolutionary confidence measurement for spoken term detection},
author={Tejedor, Javier and Echeverr{\'\i}a, Alejandro and Wang, Dong},
booktitle={Content-Based Multimedia Indexing (CBMI), 2011 9th International Workshop on},
pages={151--156},
year={2011},
organization={IEEE}
}
@article{wang2012direct,
title={Direct posterior confidence for out-of-vocabulary spoken term detection},
author={Wang, Dong and King, Simon and Frankel, Joe and Vipperla, Ravichander and Evans, Nicholas and Troncy, Rapha{\"e}l},
journal={ACM Transactions on Information Systems (TOIS)},
volume={30},
number={3},
pages={16},
year={2012},
publisher={ACM}
}
@inproceedings{tejedor2010augmented,
title={Augmented set of features for confidence estimation in spoken term detection},
author={Tejedor, Javier and Toledano, Doroteo T and Bautista, Miguel and King, Simon and Wang, Dong and Col{\'a}s, Jos{\'e}},
booktitle={Interspeech 2010},
year={2010}
}
@inproceedings{bozonnet2010integrated,
title={An integrated top-down/bottom-up approach to speaker diarization},
author={Bozonnet, Simon and Evans, Nicholas and Fredouille, Corinne and Wang, Dong and Troncy, Rapha{\"e}l},
booktitle={Interspeech 2010, September 26-30, Makuhari, Japan},
pages={Interspeech--2010},
year={2010}
}
@inproceedings{wang2010crf,
title={CRF-based stochastic pronunciation modeling for out-of-vocabulary spoken term detection},
author={Wang, Dong and King, Simon and Evans, Nicholas and Troncy, Rapha{\"e}l},
booktitle={Eleventh Annual Conference of the International Speech Communication Association},
year={2010}
}
@incollection{echeverria2010evolutionary,
title={An evolutionary confidence measure for spotting words in speech recognition},
author={Echeverr{\'\i}a, Alejandro and Tejedor, Javier and Wang, Dong},
booktitle={Trends in Practical Applications of Agents and Multiagent Systems},
pages={419--427},
year={2010},
publisher={Springer}
}
@inproceedings{wang2010stochastic,
title={Stochastic pronunciation modelling and soft match for out-of-vocabulary spoken term detection},
author={Wang, Dong and King, Simon and Frankel, Joe and Bell, Peter},
booktitle={Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on},
pages={5294--5297},
year={2010},
organization={IEEE}
}
@inproceedings{tejedor2009posterior,
title={A posterior probability-based system hybridisation and combination for spoken term detection},
author={Tejedor, Javier and Wang, Dong and King, Simon and Frankel, Joe and Col{\'a}s, Jos{\'e}},
booktitle={Interspeech 2009},
year={2009}
}
@inproceedings{wang2009term,
title={Term-dependent confidence for out-of-vocabulary term detection},
author={Wang, Dong and King, Simon and Frankel, Joe and Bell, Peter},
booktitle={Interspeech 2009},
year={2009}
}
@inproceedings{wang2009stochastic,
title={Stochastic pronunciation modelling for spoken term detection},
author={Wang, Dong and King, Simon and Frankel, Joe},
booktitle={Tenth Annual Conference of the International Speech Communication Association},
year={2009}
}
@inproceedings{wang2009posterior,
title={Posterior-based confidence measures for spoken term detection},
author={Wang, Dong and Tejedor, Javier and Frankel, Joe and King, Simon and Col{\'a}s, Jose},
booktitle={Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on},
pages={4889--4892},
year={2009},
organization={IEEE}
}
@inproceedings{frankel2008growing,
title={Growing bottleneck features for tandem ASR},
author={Frankel, Joe and Wang, Dong and King, Simon},
booktitle={Interspeech 2008},
year={2008}
}
@inproceedings{wang2008posterior,
title={A posterior approach for microphone array based speech recognition},
author={Wang, Dong and Himawan, Ivan and Frankel, Joe and King, Simon},
booktitle={Interspeech 2008},
year={2008}
}
@inproceedings{wang2008comparison,
title={A comparison of phone and grapheme-based spoken term detection},
author={Wang, Dong and Frankel, Joe and Tejedor, Javier and King, Simon},
booktitle={Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on},
pages={4969--4972},
year={2008},
organization={IEEE}
}
@article{wang2005multi,
title={Multi-layer channel normalization for frequency-dynamic feature extraction},
author={Wang, Dong and Zhu, Xian-Yan and Liu, Ying},
journal={Journal of Software},
volume={12},
number={9},
pages={1523--1529},
year={2005}
}
@inproceedings{wang2002new,
title={A New Normalization for MFCC: Multi Layer Strategy and Rrcursive Progress},
author={Wang, Dong and Hzu, Xiaoyan and Liu, Ying},
booktitle={International Symposium on Chinese Spoken Language Processing},
year={2002}
}
@inproceedings{wang2001tcmsd,
title={TCMSD: a new chinese continuous speech database},
author={Wang, Dong and Wu, Dalei and Zhu, Xiaoyan},
booktitle={International Conference on Chinese Computing (ICCC’01)},
volume={2001},
year={2001}
}
