Qingwei ZHAO


Multi-Task Learning in Deep Neural Networks for Mandarin-English Code-Mixing Speech Recognition
Mengzhe CHEN Jielin PAN Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2554-2557
Type of Manuscript:  Special Section LETTER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Acoustic modeling
Keyword: 
multi-task learningdeep neural networkMandarin-English code mixingspeech recognition
 Summary | Full Text:PDF(205.3KB)

Short Text Classification Based on Distributional Representations of Words
Chenglong MA Qingwei ZHAO Jielin PAN Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2562-2565
Type of Manuscript:  Special Section LETTER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Text classification
Keyword: 
short text classificationword embeddinggaussian model
 Summary | Full Text:PDF(171.1KB)

Speeding up Deep Neural Networks in Speech Recognition with Piecewise Quantized Sigmoidal Activation Function
Anhao XING Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2558-2561
Type of Manuscript:  Special Section LETTER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Acoustic modeling
Keyword: 
deep neural networksspeech recognitionactivation functionfixed-point quantization
 Summary | Full Text:PDF(151.4KB)

Improved End-to-End Speech Recognition Using Adaptive Per-Dimensional Learning Rate Methods
Xuyang WANG Pengyuan ZHANG Qingwei ZHAO Jielin PAN Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2550-2553
Type of Manuscript:  Special Section LETTER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Acoustic modeling
Keyword: 
connectionist temporal classificationadaptive per-dimensional learning rate methodend-to-end ASR
 Summary | Full Text:PDF(175.3KB)

Policy Optimization for Spoken Dialog Management Using Genetic Algorithm
Hang REN Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2499-2507
Type of Manuscript:  Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Spoken dialog system
Keyword: 
spoken dialog managementspoken dialog systemgenetic algorithm
 Summary | Full Text:PDF(698.7KB)

Discriminative Pronunciation Modeling Using the MPE Criterion
Meixu SONG Jielin PAN Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2015/03/01
Vol. E98-D  No. 3  pp. 717-720
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
automatic speech recognitionpronunciation modelsdiscriminative trainingMandarin conversational speech recognition
 Summary | Full Text:PDF(98.5KB)

Smoothing Method for Improved Minimum Phone Error Linear Regression
Yaohui QI Fuping PAN Fengpei GE Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2014/08/01
Vol. E97-D  No. 8  pp. 2105-2113
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speaker adaptation (SA)maximum likelihood linear regression (MLLR)maximum a posteriori linear regression (MAPLR)minimum phone error linear regression (MPELR)discriminative maximum a posteriori linear regression (DMAPLR)
 Summary | Full Text:PDF(789.4KB)

Discriminative Approach to Build Hybrid Vocabulary for Conversational Telephone Speech Recognition of Agglutinative Languages
Xin LI Jielin PAN Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2013/11/01
Vol. E96-D  No. 11  pp. 2478-2482
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
agglutinative languagesspeech recognitionsub-wordsdiscriminative learninghybrid system
 Summary | Full Text:PDF(554.1KB)

Fuzzy Matching of Semantic Class in Chinese Spoken Language Understanding
Yanling LI Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2013/08/01
Vol. E96-D  No. 8  pp. 1845-1852
Type of Manuscript:  PAPER
Category: Natural Language Processing
Keyword: 
fuzzy matchingConditional Random Field (CRF)Spoken Language Understanding (SLU)Named Entity Recognition (NER)similarity function
 Summary | Full Text:PDF(2.2MB)

A Novel Discriminative Method for Pronunciation Quality Assessment
Junbo ZHANG Fuping PAN Bin DONG Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2013/05/01
Vol. E96-D  No. 5  pp. 1145-1151
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
pronunciation assessmentautomatic scoringdistinctiveness trainingmaximum entropy
 Summary | Full Text:PDF(527.4KB)

A Forced Alignment Based Approach for English Passage Reading Assessment
Junbo ZHANG Fuping PAN Bin DONG Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/12/01
Vol. E95-D  No. 12  pp. 3046-3052
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
CALLautomatic assessmentforced alignmentformant
 Summary | Full Text:PDF(1.1MB)

Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification
Chunyan LIANG Lin YANG Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/10/01
Vol. E95-D  No. 10  pp. 2572-2576
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
speaker verificationneighborhood-preserving embeddingtotal variabilitysupport vector machinecosine distance scoring
 Summary | Full Text:PDF(73.2KB)

Noise Robust Feature Scheme for Automatic Speech Recognition Based on Auditory Perceptual Mechanisms
Shang CAI Yeming XIAO Jielin PAN Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/06/01
Vol. E95-D  No. 6  pp. 1610-1618
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
automatic speech recognitionnoise robustnesscritical bandwidthfrequency maskingtemporal masking
 Summary | Full Text:PDF(503.4KB)

Enhancing the Robustness of the Posterior-Based Confidence Measures Using Entropy Information for Speech Recognition
Yanqing SUN Yu ZHOU Qingwei ZHAO Pengyuan ZHANG Fuping PAN Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/09/01
Vol. E93-D  No. 9  pp. 2431-2439
Type of Manuscript:  Special Section PAPER (Special Section on Processing Natural Speech Variability for Improved Verbal Human-Computer Interaction)
Category: Robust Speech Recognition
Keyword: 
OOVspeech recognitionconfidence measureentropy informationphoneme-level posterior
 Summary | Full Text:PDF(1.2MB)

Acoustic Feature Optimization Based on F-Ratio for Robust Speech Recognition
Yanqing SUN Yu ZHOU Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/09/01
Vol. E93-D  No. 9  pp. 2417-2430
Type of Manuscript:  Special Section PAPER (Special Section on Processing Natural Speech Variability for Improved Verbal Human-Computer Interaction)
Category: Robust Speech Recognition
Keyword: 
mismatched speechrobust speech recognitionF-Ratiosubband designfeature optimization
 Summary | Full Text:PDF(1.2MB)

Approximate Decision Function and Optimization for GMM-UBM Based Speaker Verification
Xiang XIAO Xiang ZHANG Haipeng WANG Hongbin SUO Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2009/09/01
Vol. E92-D  No. 9  pp. 1798-1802
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
automatic speaker verificationcontribution weight re-estimationoptimization
 Summary | Full Text:PDF(1.2MB)

Using a Kind of Novel Phonotactic Information for SVM Based Speaker Recognition
Xiang ZHANG Hongbin SUO Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2009/04/01
Vol. E92-D  No. 4  pp. 746-749
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
speaker recognitionGaussian mixture modeluniversal background modelsupport vector machine
 Summary | Full Text:PDF(260.1KB)

Robust Speaker Clustering Using Affinity Propagation
Xiang ZHANG Ping LU Hongbin SUO Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/11/01
Vol. E91-D  No. 11  pp. 2739-2741
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
speaker clusteringagglomerative hierarchical clusteringaffinity propagationgeneralized likelihood ratio
 Summary | Full Text:PDF(78.2KB)

A One-Pass Real-Time Decoder Using Memory-Efficient State Network
Jian SHAO Ta LI Qingqing ZHANG Qingwei ZHAO Yonghong YAN 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/03/01
Vol. E91-D  No. 3  pp. 529-537
Type of Manuscript:  Special Section PAPER (Special Section on Robust Speech Processing in Realistic Environments)
Category: ASR System Architecture
Keyword: 
real-timememory-efficientlayer-dependent beam pruning
 Summary | Full Text:PDF(655.5KB)