Zhengqi Wen

发表

Improving BLSTM RNN based Mandarin speech recognition using accent dependent bottleneck features

Hao Ni, Jianhua Tao, Jiangyan Yi, 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

Distilling Knowledge Using Parallel Data for Far-field Speech Recognition pdf

Bin Liu, Jianhua Tao, Jiangyan Yi, 2018, ArXiv.

Improving Deep Neural Network Based Speech Synthesis through Contextual Feature Parametrization and Multi-Task Learning

Chin-Hui Lee, Zhen Huang, Jianhua Tao, 2017, Journal of Signal Processing Systems.

Investigating Deep Neural Network Adaptation for Generating Exclamatory and Interrogative Speech in Mandarin

Bin Liu, Ya Li, Jianhua Tao, 2018, J. Signal Process. Syst..

Adversarial Multilingual Training for Low-Resource Speech Recognition

Jianhua Tao, Jiangyan Yi, Zhengqi Wen, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Audio Visual Emotion Recognition with Temporal Alignment and Perception Attention pdf

Ya Li, Jianhua Tao, Zhengqi Wen, 2016, ArXiv.

Long Short Term Memory Recurrent Neural Network based Multimodal Dimensional Emotion Recognition

Ya Li, Jianhua Tao, Zhengqi Wen, 2015, AVEC@ACM Multimedia.

Transfer Learning Based Progressive Neural Networks for Acoustic Modeling in Statistical Parametric Speech Synthesis

Jianhua Tao, Zhengqi Wen, Yibin Zheng, 2018, INTERSPEECH.

Forward-Backward Decoding for Regularizing End-to-End TTS pdf

Frank K. Soong, Lei He, Zhengqi Wen, 2019, INTERSPEECH.

Investigating deep neural network adaptation for generating exclamatory and interrogative speech in Mandarin

Bin Liu, Ya Li, Jianhua Tao, 2016, 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Recurrent Neural Network Based Language Model Adaptation for Accent Mandarin Speech

Hao Ni, Jianhua Tao, Jiangyan Yi, 2016, CCPR.

Pitch-Scaled Spectrum Based Excitation Model for HMM-based Speech Synthesis

Yang Wang, Jianhua Tao, Zhengqi Wen, 2012, Journal of Signal Processing Systems.

Deep Metric Learning for the Target Cost in Unit-Selection Speech Synthesizer

Jianhua Tao, Zhengqi Wen, Yibin Zheng, 2018, INTERSPEECH.

Phoneme Dependent Speaker Embedding and Model Factorization for Multi-speaker Speech Synthesis and Adaptation

Jianhua Tao, Zhengqi Wen, Yibin Zheng, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Survey on discriminative feature selection for speech emotion recognition

Xin Xu, Hao Che, Ya Li, 2014, The 9th International Symposium on Chinese Spoken Language Processing.

On the Application and Compression of Deep Time Delay Neural Network for Embedded Statistical Parametric Speech Synthesis

Jianhua Tao, Zhengqi Wen, Yibin Zheng, 2018, INTERSPEECH.

Utterance-level Permutation Invariant Training with Discriminative Learning for Single Channel Speech Separation

Bin Liu, Jianhua Tao, Jiangyan Yi, 2018, 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP).

A novel unit selection method for concatenation speech system using similarity measure

Ran Zhang, Ya Li, Jianhua Tao, 2013, 2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE).

Context features based pre-selection and weight prediction in concatenation speech synthesis system

Bin Liu, Ya Li, Jianhua Tao, 2014, The 9th International Symposium on Chinese Spoken Language Processing.

Combining extreme learning machine and decision tree for duration prediction in HMM based speech synthesis

Yang Wang, Jianhua Tao, Zhengqi Wen, 2015, INTERSPEECH.

End-to-end keywords spotting based on connectionist temporal classification for Mandarin

Bin Liu, Ya Li, Hao Ni, 2016, 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition pdf

Jiangyan Yi, Zhengqi Wen, Jianhua Tao, 2019, INTERSPEECH.

CTC regularized model adaptation for improving LSTM RNN based multi-accent Mandarin speech recognition

Bin Liu, Hao Ni, Jianhua Tao, 2016, 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Amplitude Spectrum based Excitation Model for HMM-based Speech Synthesis

Jianhua Tao, Zhengqi Wen, J. Tao, 2012, INTERSPEECH.

The Parameterized Phoneme Identity Feature as a Continuous Real-Valued Vector for Neural Network Based Speech Synthesis

Ya Li, Jianhua Tao, Zhengqi Wen, 2016, INTERSPEECH.

A data driven method for target and concatenation cost calculation with KL-Divergence in Mandarin hybrid speech synthesis

Ya Li, Jianhua Tao, Zhengqi Wen, 2014, 2014 12th International Conference on Signal Processing (ICSP).

A novel hybrid mandarin speech synthesis system using different base units for model training and concatenation

Ran Zhang, Ya Li, Jianhua Tao, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multi-task Learning in Prediction and Correction for Low Resource Speech Recognition

Jiangyan Yi, Zhengqi Wen, Bin Liu, 2017 .

Improving Prosodic Boundaries Prediction for Mandarin Speech Synthesis by Using Enhanced Embedding Feature and Model Fusion Approach

Ya Li, Jianhua Tao, Zhengqi Wen, 2016, INTERSPEECH.

Efficient voice activity detection algorithm based on sub-band temporal envelope and sub-band long-term signal variability

Bin Liu, Ya Li, Jianhua Tao, 2014, The 9th International Symposium on Chinese Spoken Language Processing.

Learning auxiliary categorical information for speech synthesis based on deep and recurrent neural networks

Chin-Hui Lee, Zhen Huang, Jianhua Tao, 2016, 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Distilling Knowledge from an Ensemble of Models for Punctuation Prediction

Ya Li, Jianhua Tao, Jiangyan Yi, 2017, INTERSPEECH.

Improving accented Mandarin speech recognition by using recurrent neural network based language model adaptation

Bin Liu, Hao Ni, Jianhua Tao, 2016, 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Continuous Multimodal Emotion Prediction Based on Long Short Term Memory Recurrent Neural Network

Jian Huang, Ya Li, Jianhua Tao, 2017, AVEC@ACM Multimedia.

A novel method of artificial bandwidth extension using deep architecture

Bin Liu, Ya Li, Jianhua Tao, 2015, INTERSPEECH.

CLMAD: A Chinese Language Model Adaptation Dataset

Jianhua Tao, Jiangyan Yi, Zhengqi Wen, 2018, 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP).

CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandarin Speech Recognition

Bin Liu, Hao Ni, Jianhua Tao, 2018, J. Signal Process. Syst..

Acoustic Model Compression with Knowledge Transfer

Hao Ni, Jiangyan Yi, Zhengqi Wen, 2017 .

Progressive Neural Networks based Features Prediction for the Target Cost in Unit-Selection Speech Synthesizer

Jianhua Tao, Zhengqi Wen, Ruibo Fu, 2018, 2018 14th IEEE International Conference on Signal Processing (ICSP).

Long short term memory recurrent neural network based encoding method for emotion recognition in video

Ya Li, Jianhua Tao, Zhengqi Wen, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Statistical modification based post-filtering technique for HMM-based speech synthesis

Hao Che, Jianhua Tao, Zhengqi Wen, 2012, 2012 8th International Symposium on Chinese Spoken Language Processing.

Pitch-Scaled Analysis based Residual Reconstruction for Speech Analysis and Synthesis

Hideki Kawahara, Jianhua Tao, Zhengqi Wen, 2012, INTERSPEECH.

An excitation model based on inverse filtering for speech analysis and synthesis

Jianhua Tao, Zhengqi Wen, 2011, 2011 IEEE International Workshop on Machine Learning for Signal Processing.

Inverse Filtering Based Harmonic Plus Noise Excitation Model for HMM-Based Speech Synthesis

Jianhua Tao, Zhengqi Wen, J. Tao, 2011, INTERSPEECH.

Investigating Efficient Feature Representation Methods and Training Objective for BLSTM-Based Phone Duration Prediction

Bin Liu, Ya Li, Jianhua Tao, 2017, INTERSPEECH.

Speech Enhancement Based on Analysis–Synthesis Framework with Improved Parameter Domain Enhancement

Bin Liu, Jianhua Tao, Zhengqi Wen, 2016, J. Signal Process. Syst..

Investigating effect of rich syntactic features on Mandarin prosodic phrase boundaries prediction

Hao Che, Ya Li, Jianhua Tao, 2014, The 9th International Symposium on Chinese Spoken Language Processing.

Language-Adversarial Transfer Learning for Low-Resource Speech Recognition

Jianhua Tao, Jiangyan Yi, Zhengqi Wen, 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Multi-scale Temporal Modeling for Dimensional Emotion Recognition in Video

Ya Li, Jianhua Tao, Zhengqi Wen, 2014, AVEC '14.

An initial research: Towards accurate pitch extraction for speech synthesis based on BLSTM

Bin Liu, Jianhua Tao, Zhengqi Wen, 2016, 2016 IEEE 13th International Conference on Signal Processing (ICSP).

A hierarchical viterbi algorithm for Mandarin hybrid speech synthesis system

Ran Zhang, Ya Li, Bing Liu, 2014, INTERSPEECH.

Deep neural network based voice conversion with a large synthesized parallel corpus

Chin-Hui Lee, Jianhua Tao, Zhengqi Wen, 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

BLSTM-CRF Based End-to-End Prosodic Boundary Prediction with Context Sensitive Embeddings in a Text-to-Speech Front-End

Ya Li, Jianhua Tao, Zhengqi Wen, 2018, INTERSPEECH.

Text-based sentential stress prediction using continuous lexical embedding for Mandarin speech synthesis

Bin Liu, Ya Li, Jianhua Tao, 2016, 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Investigating Effect of Rich Syntactic Features on Mandarin Prosodic Boundaries Prediction

Zhengqi Wen, Jianhua Tao, Ya Li, 2016, J. Signal Process. Syst..

FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization pdf

Jianhua Tao, Jiangyan Yi, Zhengqi Wen, 2021, Interspeech.

Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data

Jianhua Tao, Jiangyan Yi, Zhengqi Wen, 2021, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Prosody and Voice Factorization for Few-Shot Speaker Adaptation in the Challenge M2voc 2021

Jianhua Tao, Jiangyan Yi, Zhengqi Wen, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Towards Fine-Grained Prosody Control for Voice Conversion

Bin Liu, Jianhua Tao, Zhengqi Wen, 2021, 2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP).

TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition pdf

Jianhua Tao, Jiangyan Yi, Zhengqi Wen, 2021, ArXiv.

Bi-Level Style and Prosody Decoupling Modeling for Personalized End-to-End Speech Synthesis

Jianhua Tao, Jiangyan Yi, Zhengqi Wen, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Text Enhancement for Paragraph Processing in End-to-End Code-switching TTS

Jianhua Tao, Jiangyan Yi, Zhengqi Wen, 2021, 2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Fast End-to-End Speech Recognition Via Non-Autoregressive Models and Cross-Modal Knowledge Transferring From BERT

Jianhua Tao, Jiangyan Yi, Zhengqi Wen, 2021, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

A BLSTM Guided Unit Selection Synthesis System for Blizzard Challenge 2016

Jianhua Tao, Zhengqi Wen, Ya Li, 2016 .

The NLPR Speech Synthesis entry for Blizzard Challenge 2020

Jianhua Tao, Zhengqi Wen, Ruibo Fu, 2020 .