LDSwap: A Semantic-Related Latent Code Disentangling Method in StyleSpace Towards High-Resolution Face Swapping.

Lifa Sun

Yu Luo Chaolin Yang Zhiyi Lin Jie Ling Lifa Sun Jinghua Zhong Tian Han 0001 LDSwap: A Semantic-Related Latent Code Disentangling Method in StyleSpace Towards High-Resolution Face Swapping. 1041-1058 2025 11 Comput. Vis. Media 5 https://doi.org/10.26599/cvm.2025.9450431 db/journals/cvm/cvm11.html#LuoYLLSZH25 streams/journals/cvm

Liyu Jin Maoxiang Yi Yuan Xiao Lifa Sun Yingchun Lu Huaguo Liang A dynamically reconfigurable entropy source circuit for high-throughput true random number generator. 105690 2023 March 133 Microelectron. J. https://doi.org/10.1016/j.mejo.2023.105690 db/journals/mj/mj133.html#JinYXSLL23

Disong Wang Songxiang Liu Xixin Wu Hui Lu Lifa Sun Xunying Liu Helen Meng Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation. 6677-6681 2022 ICASSP https://doi.org/10.1109/ICASSP43922.2022.9746680 conf/icassp/2022 db/conf/icassp/icassp2022.html#WangLWLSLM22

Disong Wang Songxiang Liu Xixin Wu Hui Lu Lifa Sun Xunying Liu Helen Meng Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation. 2022 abs/2202.09082 CoRR https://arxiv.org/abs/2202.09082 db/journals/corr/corr2202.html#abs-2202-09082

Disong Wang Songxiang Liu Lifa Sun Xixin Wu Xunying Liu Helen Meng Learning Explicit Prosody Models and Deep Speaker Embeddings for Atypical Voice Conversion. 4813-4817 2021 Interspeech https://doi.org/10.21437/Interspeech.2021-285 conf/interspeech/2021 db/conf/interspeech/interspeech2021.html#WangLSWLM21 Disong Wang Jianwei Yu 0001 Xixin Wu Lifa Sun Xunying Liu Helen Meng Improved End-to-End Dysarthric Speech Recognition via Meta-learning Based Model Re-initialization. 1-5 2021 ISCSLP https://doi.org/10.1109/ISCSLP49672.2021.9362068 conf/iscslp/2021 db/conf/iscslp/iscslp2021.html#WangYWSLM21 Songxiang Liu Disong Wang Yuewen Cao Lifa Sun Xixin Wu Shiyin Kang Zhiyong Wu 0001 Xunying Liu Dan Su 0002 Dong Yu 0001 Helen Meng End-To-End Accent Conversion Without Using Native Utterances. 6289-6293 2020 ICASSP https://doi.org/10.1109/ICASSP40776.2020.9053797 conf/icassp/2020 db/conf/icassp/icassp2020.html#LiuWCSWKWLSYM20 Disong Wang Jianwei Yu 0001 Xixin Wu Songxiang Liu Lifa Sun Xunying Liu Helen Meng End-To-End Voice Conversion Via Cross-Modal Knowledge Distillation for Dysarthric Speech Reconstruction. 7744-7748 2020 ICASSP https://doi.org/10.1109/ICASSP40776.2020.9054596 conf/icassp/2020 db/conf/icassp/icassp2020.html#WangYWLSLM20

Disong Wang Songxiang Liu Lifa Sun Xixin Wu Xunying Liu Helen Meng Learning Explicit Prosody Models and Deep Speaker Embeddings for Atypical Voice Conversion. 2020 abs/2011.01678 CoRR https://arxiv.org/abs/2011.01678 db/journals/corr/corr2011.html#abs-2011-01678

Songxiang Liu Yuewen Cao Xixin Wu Lifa Sun Xunying Liu Helen Meng Jointly Trained Conversion Model and WaveNet Vocoder for Non-Parallel Voice Conversion Using Mel-Spectrograms and Phonetic Posteriorgrams. 714-718 2019 INTERSPEECH https://doi.org/10.21437/Interspeech.2019-1316 conf/interspeech/2019 db/conf/interspeech/interspeech2019.html#LiuCWSLM19 Xixin Wu Lifa Sun Shiyin Kang Songxiang Liu Zhiyong Wu 0001 Xunying Liu Helen Meng Feature Based Adaptation for Speaking Style Synthesis. 5304-5308 2018 ICASSP https://doi.org/10.1109/ICASSP.2018.8462178 conf/icassp/2018 db/conf/icassp/icassp2018.html#WuSKLWLM18 Songxiang Liu Jinghua Zhong Lifa Sun Xixin Wu Xunying Liu Helen Meng Voice Conversion Across Arbitrary Speakers Based on a Single Target-Speaker Utterance. 496-500 2018 INTERSPEECH https://doi.org/10.21437/Interspeech.2018-1504 conf/interspeech/2018 db/conf/interspeech/interspeech2018.html#LiuZSWLM18 Songxiang Liu Lifa Sun Xixin Wu Xunying Liu Helen Meng The HCCL-CUHK System for the Voice Conversion Challenge 2018. 248-254 2018 Odyssey https://doi.org/10.21437/Odyssey.2018-35 conf/odyssey/2018 db/conf/odyssey/odyssey2018.html#LiuSWLM18 Runnan Li Zhiyong Wu 0001 Yishuang Ning Lifa Sun Helen Meng Lianhong Cai Spectro-Temporal Modelling with Time-Frequency LSTM and Structured Output Layer for Voice Conversion. 3409-3413 2017 INTERSPEECH https://doi.org/10.21437/Interspeech.2017-1122 conf/interspeech/2017 db/conf/interspeech/interspeech2017.html#LiWNSMC17 Lifa Sun Kun Li 0003 Hao Wang 0077 Shiyin Kang Helen M. Meng Phonetic posteriorgrams for many-to-one voice conversion without parallel data training. 1-6 2016 ICME https://doi.org/10.1109/ICME.2016.7552917 https://doi.ieeecomputersociety.org/10.1109/ICME.2016.7552917 conf/icmcs/2016 db/conf/icmcs/icme2016.html#SunLWKM16 Lifa Sun Hao Wang 0077 Shiyin Kang Kun Li 0003 Helen M. Meng Personalized, Cross-Lingual TTS Using Phonetic Posteriorgrams. 322-326 2016 INTERSPEECH https://doi.org/10.21437/Interspeech.2016-1043 conf/interspeech/2016 db/conf/interspeech/interspeech2016.html#SunWKLM16 Lifa Sun Shiyin Kang Kun Li 0003 Helen M. Meng Voice conversion using deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks. 4869-4873 2015 ICASSP https://doi.org/10.1109/ICASSP.2015.7178896 conf/icassp/2015 db/conf/icassp/icassp2015.html#SunKLM15 Lianhong Cai Yuewen Cao Tian Han 0001 Liyu Jin Shiyin Kang Kun Li 0003 Runnan Li Huaguo Liang Zhiyi Lin Jie Ling Songxiang Liu Xunying Liu Hui Lu Yingchun Lu Yu Luo Helen M. MengHelen Meng Yishuang Ning Dan Su 0002 Disong Wang Hao Wang 0077 Xixin Wu Zhiyong Wu 0001 Yuan Xiao Chaolin Yang Maoxiang Yi Dong Yu 0001 Jianwei Yu 0001 Jinghua Zhong