Zhijian Ou

发表

Learning Neural Trans-Dimensional Random Field Language Models with Noise-Contrastive Estimation

Bin Wang, Zhijian Ou, Bin Wang, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving and Scaling Trans-dimensional Random Field Language Models pdf

Bin Wang, Akinori Kawamura, Zhijian Ou, 2016, ArXiv.

Caption-aided speech detection in videos

Tao Wang, Wei Hu, Zhijian Ou, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Probabilistic acoustic tube: a probabilistic generative model of speech for speech analysis/synthesis

Yang Zhang, Zhijian Ou, 2012, AISTATS.

A Review of Learning with Deep Generative Models from perspective of graphical modeling pdf

Zhijian Ou, Zhijian Ou, 2018, ArXiv.

Generalized Time-Series Active Search With Kullback–Leibler Distance for Audio Fingerprinting

Hui Lin, Zhijian Ou, Xi Xiao, 2006, IEEE Signal Processing Letters.

Closely Coupled Array Processing and Model-Based Compensation for Microphone Array Speech Recognition

Zhijian Ou, Xianyu Zhao, Zhijian Ou, 2007, IEEE Transactions on Audio, Speech, and Language Processing.

Combining eigenvoice speaker modeling and VTS-based environment compensation for robust speech recognition

Zhijian Ou, Kan Deng, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Low-complexity video encoder for smart eyes based on underdetermined blind signal separation pdf

Jing Liu, Fei Qiao, Huazhong Yang, 2014, ArXiv.

Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context pdf

Zhijian Ou, Zhou Yu, Yichi Zhang, 2019, AAAI.

Semi-Supervised Seq2seq Joint-Stochastic-Approximation Autoencoders With Applications to Semantic Parsing

Zhijian Ou, Yunfu Song, 2020, IEEE Signal Processing Letters.

Learning Trans-Dimensional Random Fields with Applications to Language Modeling

Bin Wang, Zhijian Ou, Zhiqiang Tan, 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Trans-dimensional Random Fields for Language Modeling

Bin Wang, Zhijian Ou, Zhiqiang Tan, 2015, ACL.

Spoken English assessment system for non-native speakers using acoustic and prosodic features

Kun Li, Zhijian Ou, Qin Shi, 2010, INTERSPEECH.

Topic-weak-correlated Latent Dirichlet allocation

Zhijian Ou, Yimin Tan, 2010, 2010 7th International Symposium on Chinese Spoken Language Processing.

Learning Neural Random Fields with Inclusive Auxiliary Generators pdf

Zhijian Ou, Yunfu Song, Zhijian Ou, 2018, ArXiv.

Upgrading CRFS to JRFS and its Benefits to Sequence Modeling and Labeling

Zhijian Ou, Songfan Yang, Zitao Liu, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Switching Auxiliary Chains for Speech Recognition

Hui Lin, Zhijian Ou, Zhijian Ou, 2007, IEEE Signal Processing Letters.

Improved Learning of Word Embeddings with Word Definitions and Semantic Injection

Zhijian Ou, Junlan Feng, Yichi Zhang, 2020, INTERSPEECH.

CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency pdf

Zhijian Ou, Hongyu Xiang, Keyu An, 2020, INTERSPEECH.

Switching Auxiliary Chains for Speech Recognition based on Dynamic Bayesian Networks

Hui Lin, Zhijian Ou, Zhijian Ou, 2006, 18th International Conference on Pattern Recognition (ICPR'06).

Closely coupled array processing and model-based compensation for microphone array speech recognition

Zhijian Ou, Zuoying Wang, Xianyu Zhao, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

The SLT 2021 Children Speech Recognition Challenge: Open Datasets, Rules and Baselines pdf

Zhijian Ou, Lei Xie, Bo Liu, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning

Zhijian Ou, Junlan Feng, Yichi Zhang, 2020, EMNLP.

Integrating Discrete and Neural Features Via Mixed-Feature Trans-Dimensional Random Field Language Models

Zhijian Ou, Wei Yang, Huifang Xu, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Joint n-gram Chinese language modeling with an application to Chinese word segmentation

Jiasong Sun, Zhijian Ou, Xin He, 2012, 2012 International Conference on Audio, Language and Image Processing.

Joint-character-POC N-gram language modeling for Chinese speech recognition

Bin Wang, Jian Li, Akinori Kawamura, 2014, The 9th International Symposium on Chinese Spoken Language Processing.

Improvement of Probabilistic Acoustic Tube model for speech decomposition

Mark Hasegawa-Johnson, Zhijian Ou, Yang Zhang, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Eigenspace estimation with missing values and its application to eigenvoice adaptation for speech recognition

Zhijian Ou, Jun Luo, 2008, 2008 International Conference on Audio, Language and Image Processing.

Partial-tied-mixture Auxiliary Chain Models for Speech Recognition Based on Dynamic Bayesian Networks

Hui Lin, Zhijian Ou, Zhijian Ou, 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

Tracking of Enriched Dialog States for Flexible Conversational Information Access

Zhijian Ou, Pengfei Yu, Dawei Ren, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Joint Bayesian Gaussian Discriminant Analysis for speaker verification

Zhijian Ou, Yiyan Wang, Haotian Xu, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A new DP-like speaker clustering algorithm

Zhijian Ou, Zuoying Wang, 2001, INTERSPEECH.

Learning Sparse Structured Ensembles with SG-MCMC and Network Pruning pdf

Zhijian Ou, Yichi Zhang, 2018, ArXiv.

Block-wise map inference for determinantal point processes with application to change-point detection

Zhijian Ou, Martin J. Zhang, 2016, 2016 IEEE Statistical Signal Processing Workshop (SSP).

An empirical study of domain-agnostic semi-supervised learning via energy-based models: joint-training and pre-training pdf

Zhijian Ou, Yunfu Song, Huahuan Zheng, 2020, ArXiv.

CRF-based confidence measures of recognized candidates for lattice-based audio indexing

Zhijian Ou, Huaqing Luo, Zhijian Ou, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Elastic CRFs for Open-ontology Slot Filling pdf

Zhijian Ou, Junlan Feng, Yichi Zhang, 2018, ArXiv.

Combining HMM-based melody extraction and NMF-based soft masking for separating voice and accompaniment from monaural audio

Zhijian Ou, Yun Wang, Zhijian Ou, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A combined model of statics-dynamics of speech optimized using maximum mutual information

Zhijian Ou, Zuoying Wang, 2002, INTERSPEECH.

Neural CRF Transducers for Sequence Labeling

Kai Hu, Zhijian Ou, Min Hu, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models

Zhijian Ou, Yunfu Song, Zhijian Ou, 2020, UAI.

Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units

Wei Chu, Hui Lin, Zhijian Ou, 2018, 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Angular Softmax Loss for End-to-end Speaker Verification

Jiasong Sun, Feng Gao, Zhijian Ou, 2018, 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Variational nonparametric Bayesian Hidden Markov Model

Zhijian Ou, Nan Ding, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Excited commentator speech detection with unsupervised model adaptation for soccer highlight extraction

Yi Sun, Zhijian Ou, Wei Hu, 2010, 2010 International Conference on Audio, Language and Image Processing.

Improved Training Of Neural Trans-Dimensional Random field Language Models with Dynamic Noise-Contrastive Estimation

Bin Wang, Zhijian Ou, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

A new combined model of statics-dynamics of speech

Zhijian Ou, Zuoying Wang, Zuoying Wang, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Efficient Neural Architecture Search for End-to-End Speech Recognition Via Straight-Through Gradients pdf

Zhijian Ou, Keyu An, Huahuan Zheng, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

CAT: CRF-based ASR Toolkit pdf

Zhijian Ou, Hongyu Xiang, Keyu An, 2019, ArXiv.

Incorporating AM-FM effect in voiced speech for probabilistic acoustic tube model

Mark Hasegawa-Johnson, Zhijian Ou, Yang Zhang, 2015, 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

Discriminative combination of multiple linear predictions for speech recognition

Zhijian Ou, Zuoying Wang, 2004, INTERSPEECH.

Discriminative speaker adaptation with eigenvoices

Jun Luo, Zhijian Ou, Zuoying Wang, 2005, INTERSPEECH.

LEARNING SPARSE STRUCTURED ENSEMBLES WITH STOCHASTIC GRADIENT MCMC SAMPLING AND NETWORK PRUNING

Zhijian Ou, Yichi Zhang, 2018, 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP).

Calibrated adversarial algorithms for generative modelling

Zhijian Ou, Zhiqiang Tan, Yunfu Song, 2019 .

Scalable Discovery of Audio Fingerprint Motifs in Broadcast Streams With Determinantal Point Process Based Motif Clustering

Zhijian Ou, Haotian Xu, Zhijian Ou, 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Language modeling with neural trans-dimensional random fields

Bin Wang, Zhijian Ou, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

A study of large vocabulary speech recognition decoding using finite-state graphs

Zhijian Ou, Ji Xiao, 2010, 2010 7th International Symposium on Chinese Spoken Language Processing.

Use of particle filtering and MCMC for inference in Probabilistic Acoustic Tube model

Mark Hasegawa-Johnson, Zhijian Ou, Yang Zhang, 2016, 2016 IEEE Statistical Signal Processing Workshop (SSP).

Paraphrase Augmented Task-Oriented Dialog Generation pdf

Zhijian Ou, Zhou Yu, Yichi Zhang, 2020, ACL.

Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection

Zhijian Ou, Yunfu Song, 2018 .

Joint Stochastic Approximation learning of Helmholtz Machines pdf

Zhijian Ou, Haotian Xu, 2016, ArXiv.

CRF-based Single-stage Acoustic Modeling with CTC Topology

Zhijian Ou, Hongyu Xiang, Zhijian Ou, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Model Interpolation with Trans-dimensional Random Field Language Models for Speech Recognition

Akinori Kawamura, Zhijian Ou, Yong He, 2016 .

Latent Correlation Analysis of HMM Parameters for Speech Recognition

Jun Luo, Zhijian Ou, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Exploiting Single-Channel Speech For Multi-channel End-to-end Speech Recognition

Zhijian Ou, Keyu An, 2021 .

Multilingual and Crosslingual Speech Recognition Using Phonological-Vector Based Phone Embeddings pdf

Zhijian Ou, Keyu An, Huahuan Zheng, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Deformable TDNN with adaptive receptive fields for speech recognition pdf

Zhijian Ou, Keyu An, Yi Zhang, 2021, Interspeech 2021.

An Empirical Comparison of Joint-Training and Pre-Training for Domain-Agnostic Semi-Supervised Learning Via Energy-Based Models

Zhijian Ou, Huahuan Zheng, Yunfu Song, 2021, 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP).

iCallee: Recovering Call Graphs for Binaries pdf

Zhijian Ou, Zihan Zhang, Chao Zhang, 2021, ArXiv.

Advancing CTC-CRF Based End-to-End Speech Recognition with Wordpieces and Conformers pdf

Jinsong Zhang, Zhijian Ou, Huahuan Zheng, 2021, ArXiv.

Variational Latent-State GPT for Semi-supervised Task-Oriented Dialog Systems pdf

Zhijian Ou, Junlan Feng, Hong Liu, 2021, ArXiv.

The THU-SPMI CHiME-4 system : Lightweight design with advanced multi-channel processing , feature enhancement , and language modeling

Zhijian Ou, Bin Wang, Hongyu Xiang, 2016 .