081104-模式识别与智能系统

语音合成；语音识别；声纹识别；语音伪造与鉴伪

2008-09--2013-07   中科院自动化研究所   博士学位
2004-09--2008-07   中国科学技术大学   学士学位

   

2013-07~2021-06,中科院自动化研究所, 助理研究员&副研究员
2008-09~2013-07,中科院自动化研究所, 博士学位
2004-09~2008-07,中国科学技术大学, 学士学位

   

（1） 百度大脑核心技术及开放平台, 一等奖, 部委级, 2018

   

（1） Gated Recurrent Fusion With Joint Training Framework for Robust End-to-End Speech Recognition, IEEE ACM Trans. Audio Speech Lang. Process., 2021, 第 6 作者
（2） Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data, IEEE ACM Trans. Audio Speech Lang. Process., 2021, 第 4 作者
（3） Deep Time Delay Neural Network for Speech Enhancement with Full Data Learning, ISCSLP, 2021, 第 5 作者
（4） Towards Fine-Grained Prosody Control for Voice Conversion, ISCSLP, 2021, 第 3 作者
（5） Text Enhancement for Paragraph Processing in End-to-End Code-switching TTS, ISCSLP, 2021, 第 4 作者
（6） End-to-End Post-Filter for Speech Separation With Deep Attention Fusion Features, IEEE ACM Trans. Audio Speech Lang. Process., 2020, 第 5 作者
（7） A Public Chinese Dataset for Language Model Adaptation, J. Signal Process. Syst, 2020, 第 4 作者
（8） Focusing on Attention: Prosody Transfer and Adaptative Optimization Strategy for Multi-Speaker End-to-End Speech Synthesis, ICASSP, 2020, 第 3 作者
（9） Synchronous Transformers for end-to-end Speech Recognition, ICASSP, 2020, 第 6 作者
（10） Spoken Content and Voice Factorization for Few-Shot Speaker Adaptation, INTERSPEECH, 2020, 第 5 作者
（11） Dynamic Soft Windowing and Language Dependent Style Token for Code-Switching End-to-End Speech Synthesis, INTERSPEECH, 2020, 第 3 作者
（12） Gated Recurrent Fusion of Spatial and Spectral Features for Multi-Channel Speech Separation with Deep Embedding Representations, INTERSPEECH, 2020, 第 5 作者
（13） Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition, INTERSPEECH, 2020, 第 5 作者
（14） Non-Autoregressive End-to-End TTS with Coarse-to-Fine Decoding, INTERSPEECH, 2020, 第 6 作者
（15） Bi-Level Speaker Supervision for One-Shot Speech Synthesis, INTERSPEECH, 2020, 第 5 作者
（16） Joint Training for Simultaneous Speech Denoising and Dereverberation with Deep Embedding Representations, INTERSPEECH, 2020, 第 5 作者
（17） Dynamic Speaker Representations Adjustment and Decoder Factorization for Speaker Adaptation in End-to-End Speech Synthesis, INTERSPEECH, 2020, 第 3 作者
（18） ARVC: An Auto-Regressive Voice Conversion System Without Parallel Training Data, INTERSPEECH, 2020, 第 2 作者
（19） Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition, INTERSPEECH, 2020, 第 6 作者
（20） Language-Adversarial Transfer Learning for Low-Resource Speech Recognition., IEEE ACM Trans. Audio Speech Lang. Process., 2019, 第 3 作者
（21） Forward-Backward Decoding Sequence for Regularizing End-to-End TTS, IEEE ACM Trans. Audio Speech Lang. Process., 2019, 第 3 作者
（22） Noise Prior Knowledge Learning for Speech Enhancement via Gated Convolutional Generative Adversarial Network, APSIPA, 2019, 第 5 作者
（23） Voice Activity Detection Based on Time-Delay Neural Networks, APSIPA, 2019, 第 4 作者
（24） Phoneme Dependent Speaker Embedding and Model Factorization for Multi-speaker Speech Synthesis and Adaptation, ICASSP, 2019, 第 4 作者
（25） Forward-Backward Decoding for Regularizing End-to-End TTS, INTERSPEECH, 2019, 第 6 作者
（26） A Time Delay Neural Network with Shared Weight Self-Attention for Small-Footprint Keyword Spotting, INTERSPEECH, 2019, 第 4 作者
（27） Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition, INTERSPEECH, 2019, 第 5 作者
（28） Self-Attention Transducers for End-to-End Speech Recognition., INTERSPEECH, 2019, 第 5 作者
（29） Discriminative Learning for Monaural Speech Separation Using Deep Embedding Features, INTERSPEECH, 2019, 第 5 作者

   

（ 1 ） 多通道融合的音频检测与识别, 负责人, 国家任务, 2018-02--2021-12
（ 2 ） 大数据多模态交互协同关键技术, 参与, 国家任务, 2017-10--2021-09
（ 3 ） 连续状态空间个性化语音情感识别, 参与, 国家任务, 2019-01--2023-12
（ 4 ） 语音合成能力优化升级项目, 负责人, 境内委托项目, 2019-11--2021-12
（ 5 ） 伪造与鉴伪可信评价技术研究, 负责人, 国家任务, 2022-10--2024-11