IEICE Trans

Pengyuan ZHANG

Master-Teacher-Student: A Weakly Labelled Semi-Supervised Framework for Audio Tagging and Sound Event Detection Yuzhuo LIU Hangting CHEN Qingwei ZHAO Pengyuan ZHANG
Publication: Publication Date: 2022/04/01 Vol. E105-D No. 4 pp. 828-831 Type of Manuscript: LETTER Category: Speech and Hearing Keyword: sound event detection, audio tagging, semi-supervised learning, teacher-student,
	Summary \| Full Text:PDF(1MB)

A Two-Stage Attention Based Modality Fusion Framework for Multi-Modal Speech Emotion Recognition Dongni HU Chengxin CHEN Pengyuan ZHANG Junfeng LI Yonghong YAN Qingwei ZHAO
Publication: Publication Date: 2021/08/01 Vol. E104-D No. 8 pp. 1391-1394 Type of Manuscript: LETTER Category: Human-computer Interaction Keyword: speech emotion recognition, multi-modal fusion, attention mechanism, end-to-end,
	Summary \| Full Text:PDF(220.4KB)

End-to-End Multilingual Speech Recognition System with Language Supervision Training Danyang LIU Ji XU Pengyuan ZHANG
Publication: Publication Date: 2020/06/01 Vol. E103-D No. 6 pp. 1427-1430 Type of Manuscript: LETTER Category: Speech and Hearing Keyword: multilingual speech recognition, language-adaptive training, hybrid attention/CTC,
	Summary \| Full Text:PDF(258.7KB)

Automatic Speech Recognition System with Output-Gate Projected Gated Recurrent Unit Gaofeng CHENG Pengyuan ZHANG Ji XU
Publication: Publication Date: 2019/02/01 Vol. E102-D No. 2 pp. 355-363 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: GRU, LSTM, neural network language model, speech recognition,
	Summary \| Full Text:PDF(747.8KB)

Speaker-Phonetic I-Vector Modeling for Text-Dependent Speaker Verification with Random Digit Strings Shengyu YAO Ruohua ZHOU Pengyuan ZHANG
Publication: Publication Date: 2019/02/01 Vol. E102-D No. 2 pp. 346-354 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: speaker verification, text-dependent, speaker-phonetic, random digit strings, i-vector, phonetically-constrained,
	Summary \| Full Text:PDF(1.2MB)

Improve Multichannel Speech Recognition with Temporal and Spatial Information Yu ZHANG Pengyuan ZHANG Qingwei ZHAO
Publication: Publication Date: 2018/07/01 Vol. E101-D No. 7 pp. 1963-1967 Type of Manuscript: LETTER Category: Speech and Hearing Keyword: multichannel speech recognition, long short-term memory, attention mechanism, generalized cross correlation,
	Summary \| Full Text:PDF(692.6KB)

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 classification, adaptive per-dimensional learning rate method, end-to-end ASR,
	Summary \| Full Text:PDF(175.3KB)

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: OOV, speech recognition, confidence measure, entropy information, phoneme-level posterior,
	Summary \| Full Text:PDF(1.2MB)