Papers


2019

Yanmin Qian and Xu Xiang Binary Neural Networks for Speech Recognition Journal FITEE PDF
Yanmin Qian, Hu Hu and Tian Tan Data Augmentation Using Generative Adversarial Networks for Robust Speech Recognition. Speech Communication, vol Journal SC PDF
Lu Chen, Zhi Chen, Bowen Tan, Sishan Long, Milica Gasic and Kai Yu AgentGraph: Toward Universal Dialogue Management With Structured Deep Reinforcement Learning. IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 9, pp. 1378-1391, Sep. 2019 Journal IEEE/ACM Transactions on Audio, Speech, and Language Processing PDF
Shuai Wang, Zili Huang, Yanmin Qian and Kai Yu Discriminative Neural Embedding Learning for Short-Duration Text-Independent Speaker Verification. IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 11, pp. 1686-1696, Nov. 2019 Journal IEEE/ACM Transactions on Audio, Speech, and Language Processing PDF
Xu Xiang, Shuai Wang, Houjun Huang, Yanmin Qian and Kai Yu Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition Conference APSIPA PDF
Xuankai Chang, Wangyou Zhang, Yanmin Qian, Jonathan Le Roux and Shinji Watanabe MIMO-Speech: End-to-End Multi-Channel Multi-Speaker Speech Recognition Conference ASRU PDF
Wangyou Zhang, Man Sun, Lan Wang and Yanmin Qian End-to-End Overlapped Speech Detection and Speaker Counting with Raw Waveform Conference ASRU PDF
Mingkun Huang, Yizhou Lu, Lan Wang, Yanmin Qian and Kai Yu Exploring Model Units and Training Strategies for End-to-End Speech Recognition Conference ASRU PDF
Rao Ma, Qi Liu and Kai Yu Highly Efficient Neural Network Language Model Compression Using Soft Binarization Training Conference ASRU PDF
Peiyao Sheng, Zhuolin Yang and Yanmin Qian GANs for Children: A Generative Data Augmentation Strategy for Children Speech Recognition Conference ASRU PDF
Zijian Zhao, Su Zhu and Kai Yu Data Augmentation with Atomic Templates for Spoken Language Understanding Conference EMNLP PDF
Yefei Chen, Shuai Wang, Yanmin Qian and Kai Yu End-to-End Speaker-Dependent Voice Activity Detection Conference NCMMSC PDF
Hao Li, Zhehuai Chen, Qi Liu, Yanmin Qian and Kai Yu OOV Words Extension for Modular Neural Acoustics-to-Word Model Conference NCMMSC PDF
Hao Li, Chen Liu, Su Zhu and Kai Yu Robust Spoken Language Understanding with Acoustic and Domain Knowledge Conference ICMI PDF
Su Zhu, Zijian Zhao, Tiejun Zhao, Chengqing Zong and Kai Yu CATSLU: The 1st Chinese Audio-Textual Spoken Language Understanding Challenge Conference ICMI PDF
Zhehuai Chen, Mahaveer Jain, Yongqiang Wang, Michael Seltzer and Christian Fuegen Joint Grapheme and Phoneme Embeddings for Contextual End-to-End ASR Conference InterSpeech PDF
Jiaqi Guo, Yongbin You, Yanmin Qian and Kai Yu Joint Decoding of CTC Based Systems for Speech Recognition Conference InterSpeech PDF
Chenda Li and Yanmin Qian Prosody Usage Optimization for Children Speech Recognition with Zero Resource Children Speech Conference InterSpeech PDF
Wangyou Zhang, Xuankai Chang and Yanmin Qian Knowledge Distillation for End-to-End Monaural Multi-talker ASR System Conference InterSpeech PDF
Wangyou Zhang, Ying Zhou and Yanmin Qian Robust DOA Estimation Based on Convolutional Neural Network and Time-Frequency Masking Conference InterSpeech PDF
Zhanghao Wu, Shuai Wang, Yanmin Qian and Kai Yu Data Augmentation using Variational Autoencoder for Embedding based Speaker Verification Conference InterSpeech PDF
Yexin Yang, Hongji Wang, Heinrich Dinkel, Zhengyang Chen, Shuai Wang, Yanmin Qian and Kai Yu The SJTU Robust Anti-spoofing System for the ASVspoof 2019 Challenge Conference InterSpeech PDF
Hongji Wang, Heinrich Dinkel, Shuai Wang, Yanmin Qian and Kai Yu Cross-domain Replay Spoofing Attack Detection using Domain Adversarial Training Conference InterSpeech PDF
Shuai Wang, Johan Rohdin, Lukáš Burget, Oldřich Plchot, Yanmin Qian, Kai Yu and Jan Černocký On the Usage of Phonetic Information for Text-independent Speaker Embedding Extraction Conference InterSpeech PDF
Mireia Diez, Lukáš Burget, Shuai Wang, Johan Rohdin and Jan Černocký Bayesian HMM based x-vector clustering for Speaker Diarization Conference InterSpeech PDF
Ruisheng Cao, Su Zhu, Chen Liu, Jieyu Li and Kai Yu Semantic Parsing with Dual Learning Conference ACL PDF
Mengyue Wu, Heinrich Dinkel and Kai Yu Audio Caption: Listen and Tell Conference ICASSP PDF
Zhehuai Chen, Mahaveer Jain, Yongqiang Wang, Michael Seltzer and Christian Fuegen End-to-end Contextual Speech Recognition using Class Language Models and a Token Passing Decoder Conference ICASSP PDF
Zijian Zhao, Su Zhu and Kai Yu A Hierarchical Decoding Model for Spoken Language Understanding from Unaligned Data Conference ICASSP PDF
Shuai Wang, Yexin Yang, Tianzhe Wang, Yanmin Qian and Kai Yu Knowledge Distillation for Small Foot-print Deep Speaker Embedding Conference ICASSP PDF
Xuankai Chang, Yanmin Qian, Kai Yu and Shinji Watanabe End-to-end Monaural Multi-speaker ASR System without Pretraining Conference ICASSP PDF

2018

Zhehuai Chen, Jasha Droppo, Jinyu Li, Wayne Xiong Progressive Joint Modeling in Unsupervised Single-channel Overlapped Speech Recognition Journal IEEE/ACM Transactions on Audio, Speech, and Language Processing PDF
Tian Tan, Yanmin Qian, Hu Hu, Wen Ding, Ying Zhou, Kai Yu Adaptive very deep convolutional residual network for noise robust speech recognition Journal IEEE/ACM Transactions on Audio, Speech, and Language Processing PDF
Kai Yu, Zijian Zhao, Xueyang Wu, Hongtao Lin and Xuan Liu Rich Short Text Conversation Using Semantic Key Controlled Sequence Generation Journal IEEE/ACM Transactions on Audio, Speech, and Language Processing PDF
Xuan Liu, Di Cao and Kai Yu Binarized LSTM Language Model Conference NAACL PDF
Ying Zhou and Yanmin Qian Robust Mask Estimation by Integrating Neural Network-Based and Clustering-Based Approaches for Adaptive Acoustic Beamforming Conference ICASSP PDF
Lu Chen, Cheng Chang, Zhi Chen, Bowen Tan, Milica Gasic and Kai Yu Policy Adaptation for Deep Reinforcement Learning-based Dialogue Management Conference ICASSP PDF
Shuai Wang, Yanmin Qian and Kai Yu Focal KL-Divergence based Dilated Convolutional Neural Networks for Co-channel Speaker Identification Conference ICASSP PDF
Ruinian Chen and Kai Yu Fast OOV Words Incorporation using Structured Word Embeddings for Neural Network Language Model Conference ICASSP PDF
Hu Hu, Tian Tan and Yan min Qian Generative Adversarial Networks based Data Augmentation for Noise Robust Speech Recognition Conference ICASSP PDF
Wen Ding, Tian Tan and Yanmin Qian Fast Adaptation on Deep Mixture Generative Network Based Acoustic Modeling Conference ICASSP PDF
Xuankai Chang, Yanmin Qian and Dong Yu Adaptive Permutation Invariant Training with Auxiliary Information for Monaural Multi-Talker Speech Recognition Conference ICASSP PDF
Tian Tan, Yanmin Qian and Dong Yu Knowledge Transfer in Permutation Invariant Training for Single-channel Multi-talker Speech Recognition Conference ICASSP PDF
Zhehuai Chen, Qi Liu, Hao Li, Kai Yu On Modular Training of Neural Acoustics-to-word Model for LVCSR Conference ICASSP PDF
Zhehuai Chen, Jasha Droppo Sequence Modeling in Unsupervised Single-channel Overlapped Speech Recognition Conference ICASSP PDF
Su Zhu, Ouyu Lan, Kai Yu Robust Spoken Language Understanding with Unsupervised ASR-error Adaptation Conference ICASSP PDF
Ouyu Lan, Su Zhu, Kai Yu Semi-Supervised Training Using Adversarial Multi-Task Learning for Spoken Language Understanding Conference ICASSP PDF
Zili Huang, Shuai Wang and Yanmin Qian Joint I-Vector with End-to-End System for Short Duration Text-Independent Speaker Verification Conference ICASSP PDF

2017

Yanmin Qian, Nanxin Chen, Heinrich Dinkel and Zhizheng Wu Deep Feature Engineering for Noise Robust Spoofing Detection Journal IEEE/ACM Transactions on Audio, Speech, and Language Processing PDF
Zhehuai Chen, Yimeng Zhuang, Yanmin Qian and Kai Yu Phone Synchronous Speech Recognition with CTC Lattices Journal IEEE/ACM Transactions on Audio, Speech, and Language Processing PDF
Ruinian Chen, Ying Zhou and Yanmin Qian Emotion Recognition Using Support Vector Machine and Deep Neural Network Conference NCMMSC PDF
Cheng Chang, Huifeng Zhang, Zhangxuan Gu and Yanmin Qian Fusion Model for Speech Emotion Recognition with Low Level Descriptor Features Conference NCMMSC PDF
Yue Wu, Qi Liu, Kai Yu The adaptive adjustment of learning rate is applied in the language model Conference NCMMSC PDF
Xuan Liu, Kai Yu GLEU-Guided Multi-resolution Network for Short Text Conversation Conference NCMMSC PDF
Kaiyu Shi, Xuan Liu and Yanmin Qian Speech Emotion Recognition Based on SVM and GMM-HMM Hybrid System Conference NCMMSC PDF
Yue Wu, Tianxing He, Zhehuai Chen, Yanmin Qian, Kai Yu Multi-view LSTM Language Model with Word-synchronized Auxiliary Feature for LVCSR Conference CCL PDF
Zhehuai Chen, Yanmin Qian, and Kai Yu A unified confidence measure framework using auxiliary normalization graph Conference IScIDE PDF
Di Cao and Kai Yu Deep Attentive Structured Language Model Based on LSTM Conference IScIDE PDF
Xiaowei Jiang, Shuai Wang, Xu Xiang and Yanmin Qian Integrating Online i-vector into GMM-UBM for Text-dependent Speaker Verification Conference APSIPA PDF
Qi Liu, Yanmin Qian and Kai Yu Future Vector Enhanced LSTM Language Model for LVCSR Conference ASRU PDF
Lu Chen, Xiang Zhou, Cheng Chang, Runzhe Yang and Kai Yu Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning Conference EMNLP PDF
Cheng Chang, Runzhe Yang, Lu Chen, Xiang Zhou and Kai Yu Affordable On-line Dialogue Policy Learning Conference EMNLP PDF
Xu Xiang, Yanmin Qian and Kai Yu Binary Deep Neural Networks for Speech Recognition Conference InterSpeech PDF
Dong Yu, Xuankai Chang and Yanmin Qian Recognizing Multi-Talker Speech with Permutation Invariant Trainin Conference InterSpeech PDF
Bo Chen, Jiahao Lai and Kai Yu Comparison of Modeling Target in LSTM-RNN Duration Model Conference InterSpeech PDF
Bo Chen, Tianling Bian and Kai Yu Discrete Duration Model For Speech Synthesis Conference InterSpeech PDF
Shuai Wang, Yanmin Qian and Kai Yu What Does the Speaker Embedding Encode? Conference InterSpeech PDF
Heinrich Dinkel, Yanmin Qian, Kai Yu Small-footprint convolutional neural network for spoofing detection Conference IJCNN PDF
Lu Chen, Runzhe Yang, Cheng Chang, Zihao Ye, Xiang Zhou and Kai Yu On-line Dialogue Policy Learning with Companion Teaching Conference EACL PDF
Heinrich Dinkel, Nanxin Chen, Yanmin Qian and Kai Yu End-To-End Spoofing Detection With Raw Waveform Cldnns Conference ICASSP PDF
Su Zhu and Kai Yu Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understanding Conference ICASSP PDF
Zhehuai Chen, Yimeng Zhuang and Kai Yu Confidence Measures for CTC-based Phone Synchronous Decoding Conference ICASSP PDF