| Mockingjay: Unsupervised speech representation learning with deep bidirectional transformer encoders AT Liu, S Yang, PH Chi, P Hsu, H Lee ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 418 | 2020 |
| Investigating on incorporating pretrained and learnable speaker representations for multi-speaker multi-style text-to-speech CM Chien, JH Lin, C Huang, P Hsu, H Lee ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 72 | 2021 |
| Unsupervised end-to-end learning of discrete linguistic units for voice conversion AT Liu, P Hsu, H Lee arXiv preprint arXiv:1905.11563, 2019 | 32 | 2019 |
| Stop: A dataset for spoken task oriented semantic parsing P Tomasello, A Shrivastava, D Lazar, PC Hsu, D Le, A Sagar, A Elkahky, ... 2022 IEEE Spoken Language Technology Workshop (SLT), 991-998, 2023 | 29 | 2023 |
| Rhythm-flexible voice conversion without parallel data using cycle-gan over phoneme posteriorgram sequences C Yeh, P Hsu, J Chou, H Lee, L Lee 2018 IEEE Spoken Language Technology Workshop (SLT), 274-281, 2018 | 28 | 2018 |
| Towards robust neural vocoding for speech generation: A survey P Hsu, C Wang, AT Liu, H Lee arXiv preprint arXiv:1912.02461, 2019 | 27 | 2019 |
| WG-WaveNet: Real-time high-fidelity speech synthesis without GPU P Hsu, H Lee arXiv preprint arXiv:2005.07412, 2020 | 22 | 2020 |
| Adversarial sample detection for speaker verification by neural vocoders H Wu, PC Hsu, J Gao, S Zhang, S Huang, J Kang, Z Wu, H Meng, HY Lee ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 20 | 2022 |
| Spotting adversarial samples for speaker verification by neural vocoders H Wu, P Hsu, J Gao, S Zhang, S Huang, J Kang, Z Wu, H Meng, H Lee arXiv preprint arXiv:2107.00309, 2021 | 9 | 2021 |
| Learning phone recognition from unpaired audio and phone sequences based on generative adversarial network D Liu, P Hsu, Y Chen, S Huang, S Chuang, D Wu, H Lee IEEE/ACM transactions on audio, speech, and language processing 30, 230-243, 2021 | 7 | 2021 |
| Silence is sweeter than speech: Self-supervised model using silence to store speaker information CL Feng, P Hsu, H Lee arXiv preprint arXiv:2205.03759, 2022 | 6 | 2022 |
| Parallel synthesis for autoregressive speech generation P Hsu, DR Liu, AT Liu, H Lee IEEE/ACM Transactions on Audio, Speech, and Language Processing 31, 3095-3111, 2023 | 4 | 2023 |
| Low-Resource Self-Supervised Learning with SSL-Enhanced TTS P Hsu, A Elkahky, WN Hsu, Y Adi, TA Nguyen, J Copet, E Dupoux, H Lee, ... arXiv preprint arXiv:2309.17020, 2023 | | 2023 |
| Universal Adaptor: Converting Mel-Spectrograms Between Different Configurations for Speech Synthesis FL Wang, P Hsu, D Liu, H Lee arXiv preprint arXiv:2204.00170, 2022 | | 2022 |
Hung-yi LeeNational Taiwan University在 ntu.edu.tw 的电子邮件经过验证
