├── LICENSE └── README.md /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Awesome-Voice-Conversion-Papers-Projects 2 | Here are some interesting papers in speech field which I collected, may they help you. 3 | ## Update Project 4 | 5 | :heavy_check_mark: Mancusi, Michele, et al. "**Latent Diffusion Bridges for Unsupervised Musical Audio Timbre Transfer.**" arXiv preprint arXiv:2409.06096 (2024). [[Paper]](https://arxiv.org/abs/2409.06096) [[Project]](https://github.com/sony/diffusion-timbre-transfer) 6 | 7 | :heavy_check_mark: Biadsy, Fadi, et al. "**Zero-shot Cross-lingual Voice Transfer for TTS.**" arXiv preprint arXiv:2409.13910 (2024). [[Paper]](https://arxiv.org/pdf/2409.13910) 8 | 9 | ## Overview 10 | 11 | - [Voice Conversion](#Voice-Conversion) 12 | 13 | - [Singing Voice Conversion](#Singing-Voice-Conversion) 14 | 15 | - [Interesting papers](#Interesting-papers) 16 | 17 | 18 | ### Voice Conversion 19 | 20 | #### 1. Challenge 21 | 22 | Voice Conversion Challenge（VCC）[[Home]](https://link.zhihu.com/?target=http%3A//www.vc-challenge.org/) 23 | 24 | ZeroSpeech Challenge [[Home]](https://link.zhihu.com/?target=https%3A//zerospeech.com/2020/news.html) 25 | 26 | #### 2. Dataset 27 | 28 | [[VCTK]](https://datashare.is.ed.ac.uk/handle/10283/3443) 29 | 30 | [[ZeroSpeech 2020]](https://link.zhihu.com/?target=https%3A//download.zerospeech.com/) 31 | 32 | [[VCC2016]](https://link.zhihu.com/?target=https%3A//datashare.is.ed.ac.uk/handle/10283/2211) The Voice Conversion Challenge 2016 33 | 34 | [[VCC2018]](https://link.zhihu.com/?target=https%3A//datashare.is.ed.ac.uk/handle/10283/3061) The Voice Conversion Challenge 2018 35 | 36 | 37 | #### 3. Method 38 | 39 | ##### 3.1 Parallel VC 40 | [VCC 2018 Baseline](https://link.zhihu.com/?target=https%3A//github.com/k2kobayashi/sprocket) 41 | 42 | 43 | ##### 3.2 Non-parallel VC 44 | 45 | ###### 3.2.1 Direct Conversion： 46 | 47 | - **CycleGAN-VC** (*arXiv:1711.11293, Nov. 2017 (EUSIPCO, 2018)*) author info: Takuhiro Kaneko Hirokazu Kameoka NTT Communication Science Laboratories, NTT Corporation 48 | 49 | - **CycleGAN-VC2** (*arXiv:1904.04631, Apr. 2019 ICASSP 2019*) author info: Takuhiro Kaneko Hirokazu Kameoka Kou Tanaka Nobukatsu HojoNTT Communication Science Laboratories, NTT Corporation 50 | 51 | - **StarGAN-VC** (*arXiv:1806.02169, June 2018 (SLT, 2018)*) author info: Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu HojoNTT Communication Science Laboratories, NTT Corporation 52 | 53 | - **VAW-GAN-VC** (*arXiv:1704.00849, 4 Apr 2017. Interspeech, 2017*) author info: Chin-Cheng Hsu , Hsin-Te Hwang , Yi-Chiao Wu , Yu Tsao, and Hsin-Min Wang Institute of Information Science, Academia Sinica, Taiwan ，Research Center for Information Technology Innovation, Academia Sinica, Taiwan 54 | 55 | - **StarGAN-VC2** (*arXiv:1907.12279, July 2019 Interspeech 2019*) author info: Takuhiro Kaneko Hirokazu Kameoka Kou Tanaka Nobukatsu HojoNTT Communication Science Laboratories, NTT Corporation 56 | 57 | - **Contrastive Voice Conversion** (CVC) non-parallel voice conversion based on patch-wise contrastive learning and adversarial learning 58 | 59 | ###### 3.2.2 Feature Disentangle: 60 | 61 | - **SGAN-VC** (*arXiv preprint arXiv:2207.06057 (2022)*) Subband-based Generative Adversarial Network for Non-parallel Many-to-many Voice Conversion. [[Demo]](https://hechang25.github.io/SGAN-VC/) [[Paper]](https://arxiv.org/pdf/2207.06057.pdf) 62 | 63 | - **AUTO-VC** (*arXiv preprint arXiv:1905.05879 (2019)*) author info: Kaizhi Qian, Yang Zhang, Shiyu Chang, Xuesong Yang, Mark Hasegawa-Johnson University of Illinois at UrbanaChampaign, IL, USA , MIT-IBM Watson AI Lab, Cambridge, MA, USA , IBM Research, Cambridge, MA, USA. 64 | 65 | - **CDVAE-VC** Unsupervised Representation Disentanglement Using Cross Domain Features and Adversarial Learning in Variational Autoencoder Based Voice Conversion 66 | 67 | - **ACVAE-VC** (*arXiv:1808.05092, Aug. 2018. (IEEE/ACM Transactions on Audio, Speech, and Language Processing, May 2019)*) author info: Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu HojoNTT Communication Science Laboratories, NTT Corporation 68 | 69 | - **SpeechSplit** (*arXiv preprint arXiv:2004.11284 (2020)*) author info: Kaizhi Qian, Yang Zhang, Shiyu Chang, David Cox, Mark Hasegawa-Johnson MIT-IBM Watson AI Lab, USA University of Illinois at Urbana-Champaign, USA. 70 | 71 | - **AGAIN-VC** AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization (2020) 72 | 73 | - **Crank** Non-parallel voice conversion based on vector-quantized variational autoencoder with adversarial learning author info：Kazuhiro Kobayashi Wen-Chin Huang Tomoki Toda 74 | 75 | - **VQ-VAE-Speech** VQ-VAE + WaveNet by [*Chorowski et al., 2019*] and VQ-VAE on speech signals by [*van den Oord et al., 2017*]. 76 | 77 | - **VQ-VAE** for Acoustic Unit Discovery and Voice Conversion Train and evaluate the VQ-VAE model for the ZeroSpeech 2020 challenge. 78 | 79 | - **RandomCNN-voice-transfer** Maybe the fastest voice style transfer with reasonable result 80 | 81 | - **FragmentVC** (arXiv preprint arXiv:2010.14150(2020)). author info: Yist Y. Lin, Chung-Ming Chien, Jheng-Hao Lin, Hung-yi Lee, Lin-shan Lee, National Taiwan University College of Electrical Engineering and Computer Science 82 | 83 | - **HVQ-VAE** Cross-lingual Voice Conversion using Hierarchical Vector-Quantized Variational Autoencoder author info: Tuan Vu Ho and Masato Akagi Japan Advanced Institute of Science and Technology （VCC2020） 84 | 85 | - **CycleVAE** Provides a Cyclic Variational AutoEncoder (CycleVAE)-based voice conversion (VC) system with parallel WaveGAN (PWG)-based vocoder for Voice Conversion Challenge 2020 (VCC2020) 86 | 87 | - Voice Conversion on unaligned data compare standard VAE, VQ-VAE and Gumbel VAE models as approaches to VC on the Voice Conversion Challenge 2016 dataset. 88 | 89 | - **ZeroSpeech 2019:** TTS without T - Pytorch "Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion", Interspeech 2019. 2nd place in terms of low bitrate, higher Mean Opinion Score (MOS) and lower CER than the 1st place team 90 | 91 | - **Cascade ASR + TTS** Recipe for Voice Conversion Challenge 2020 baseline: Cascade ASR + TTS author info: Wen-Chin Huang @ Nagoya University Tomoki Hayashi Shinji Watanabe (JHU), Tomoki Toda (Nagoya U) 92 | 93 | - **MelGAN-VC** MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms 94 | 95 | - **Cotatron** Cotatron: Transcription-Guided Speech Encoder for Any-to-Many Voice Conversion without Parallel Data author info: Seung-won Park , Doo-young Kim, Myun-chul Joe2 1Seoul National University 2MINDsLab Inc. 96 | 97 | - Voice Conversion with Non-Parallel Data Phonetic posteriorgrams for many-to-one voice conversion without parallel data training (PPGs based) 98 | 99 | - Voice-Conversion Multi-target voice conversion without parallel data by adversarially learning disentangled audio representations.(2018) 100 | 101 | - Voice Conversion Compare with Standard VAE, VQ-VAE and Gumbel VAE models, JointVAE approaches on the VCC 2016 dataset. 102 | 103 | - **Wavenet_AutoEncoders**(ZeroSpeech 2020 challenge)WaveNet autoencoder + Instance Normalization (IN-WAE) WaveNet autoencoder + Sliced Vector Quantization (SVQ-WAE) 104 | 105 | - Adversarial Voice Conversion Voice conversion using deep adversarial learning, based on WaveNet autoencoders. multiple decoders are used so that each one corresponds to a particular voice. adversarial domain adaptation technique is employed (2019) 106 | 107 | - **Adversarial-Many-to-Many-VC** Improving the Speaker Identity of Non-Parallel Many-to-Many Voice Conversion with Adversarial Speaker Recognition(PPG2speech synthesizer with adversarial speaker classifier) 108 | 109 | - **TransferLearning-CLVC** "Transfer Learning from Monolingual ASR to Transcription-free Cross-lingual Voice Conversion." author info: Che-Jui Chang Red Pill Lab（PPGs + Waveglow vocoder） 110 | 111 | - **Non-parallel Seq2seq Voice Conversion** Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representations (2019)(PPGs based end2end train) 112 | 113 | - **EA-SVC** Phonetic Posteriorgrams based Many-to-Many Singing Voice Conversion via Adversarial Training(PPG based SVC) 114 | 115 | - **Audio-Style-Transfer** Neural Style Transfer for Audio Spectrograms 116 | 117 | ##### 4. Paper & Projects 118 | 119 | :heavy_check_mark: Huang, Jiawei, et al. "**MulliVC: Multi-lingual Voice Conversion With Cycle Consistency.**" arXiv preprint arXiv:2408.04708 (2024). [[Paper]](https://arxiv.org/pdf/2408.04708) 120 | 121 | :heavy_check_mark: Yang, Yang, et al. "**StreamVC: Real-Time Low-Latency Voice Conversion.**" arXiv preprint arXiv:2401.03078 (2024)." [[Paper]](https://arxiv.org/abs/2401.03078) [[unofficial implementation1]](https://github.com/hrnoh24/stream-vc) [[unofficial implementation2]](https://github.com/yuval-reshef/StreamVC) 122 | 123 | :heavy_check_mark: -Oh, Hyoung-Seok, et al. "**DurFlex-EVC: Duration-Flexible Emotional Voice Conversion with Parallel Generation.**" arXiv preprint arXiv:2401.08095 (2024). [[Paper]](https://arxiv.org/pdf/2401.08095v1.pdf) [[Project]](https://github.com/hs-oh-prml/durflexevc)) 124 | 125 | :heavy_check_mark: -Choi, Ha-Yeong, Sang-Hoon Lee, and Seong-Whan Lee. "**Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation.**" arXiv preprint arXiv:2311.04693 (2023). [[Paper]](https://arxiv.org/abs/2311.04693) [[Project]](https://github.com/hayeong0/Diff-HierVC)) 126 | 127 | :heavy_check_mark: -Sadov, Konstantine, Matthew Hutter, and Asara Near. "**Low-latency Real-time Voice Conversion on CPU.**" arXiv preprint arXiv:2311.00873 (2023). [[Paper]](https://koe.ai/papers/llvc.pdf) [[Project]](https://github.com/KoeAI/LLVC)) 128 | 129 | :heavy_check_mark: -Shan, Siyuan, et al. "**Phoneme Hallucinator: One-shot Voice Conversion via Set Expansion.**" arXiv preprint arXiv:2308.06382 (2023). [[Paper]](https://arxiv.org/abs/2308.06382) [[Project]](https://github.com/PhonemeHallucinator/Phoneme_Hallucinator)) 130 | 131 | :heavy_check_mark: -Kang, Wonjune, Mark Hasegawa-Johnson, and Deb Roy. "**End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions.**" arXiv preprint arXiv:2205.09784 (2022). [[Paper]](https://arxiv.org/abs/2205.09784) [[Project]](https://github.com/wonjune-kang/lvc-vc)) 132 | 133 | :heavy_check_mark: -Baas, Matthew, Benjamin van Niekerk, and Herman Kamper. "**Voice Conversion With Just Nearest Neighbors.**" arXiv preprint arXiv:2305.18975 (2023). [[Paper]](https://arxiv.org/pdf/2305.18975.pdf) [[Project]](https://github.com/bshall/knn-vc)) 134 | 135 | :heavy_check_mark: -Li, Yinghao Aaron, Cong Han, and Nima Mesgarani. "**Styletts-vc: One-shot voice conversion by knowledge transfer from style-based tts models.**" 2022 IEEE Spoken Language Technology Workshop (SLT). IEEE, 2023. [[Paper]](https://arxiv.org/abs/2212.14227) [[Project]](https://github.com/yl4579/StyleTTS-VC) 136 | 137 | :heavy_check_mark: - Lu, Hui, et al. "**Disentangled Speech Representation Learning for One-Shot Cross-Lingual Voice Conversion Using ß-VAE.**" 2022 IEEE Spoken Language Technology Workshop (SLT). IEEE, 2023. [[Paper]](https://www1.se.cuhk.edu.hk/~hccl/publications/pub/2023%20SLT2022-Beta_VAE_based_one_shot_cross_lingual_VC.pdf) [[Project]](https://github.com/light1726/BetaVAE_VC) 138 | 139 | :heavy_check_mark: - Park, Hyun Joon, et al. "**TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion.**" [[Paper]](https://arxiv.org/abs/2303.09057) [[Project]](https://github.com/winddori2002/TriAAN-VC) 140 | 141 | :heavy_check_mark: - Li, Jingyi, Weiping Tu, and Li Xiao. "**FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion.**"[[Paper]](https://arxiv.org/abs/2210.15418) [[Project]](https://github.com/OlaWod/FreeVC) 142 | 143 | :heavy_check_mark: - Kashkin, Anton, Ivan Karpukhin, and Svyatoslav Shishkin. "**HiFi-VC: High Quality ASR-Based Voice Conversion.**" arXiv preprint arXiv:2203.16937 (2022)..[[Paper]](https://arxiv.org/abs/2203.16937) [[Project]](https://github.com/tinkoff-ai/hifi_vc) 144 | 145 | :heavy_check_mark: - Yuan, Ruibin, et al. "**DeID-VC: Speaker De-identification via Zero-shot Pseudo Voice Conversion.**" arXiv preprint arXiv:2209.04530 (2022).[[Paper]](https://arxiv.org/abs/2209.04530) [[Project]](https://github.com/a43992899/DeID-VC) 146 | 147 | :heavy_check_mark: - Popov, Vadim, et al. "**Diffusion-based voice conversion with fast maximum likelihood sampling scheme.**" arXiv preprint arXiv:2109.13821 (2021). [[Paper]](https://arxiv.org/pdf/2109.13821.pdf) [[Project]](https://github.com/huawei-noah/Speech-Backbones/tree/main/DiffVC) 148 | 149 | :heavy_check_mark: - Nguyen, Bac, and Fabien Cardinaux. "**Nvc-net: End-to-end adversarial voice conversion.**" ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022. [[Paper]](https://arxiv.org/abs/2106.00992) [[Project]](https://github.com/sony/ai-research-code/tree/master/nvcnet) 150 | 151 | :heavy_check_mark: - Zhao, Xintao, et al. "**Disentangling Content and Fine-Grained Prosody Information Via Hybrid ASR Bottleneck Features for Voice Conversion.**" ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022.. [[Paper]](https://arxiv.org/pdf/2203.12813.pdf) [[Project]](https://thuhcsi.github.io/icassp2022-hybrid-bottleneck-vc/) 152 | 153 | :heavy_check_mark: - Liu, Songxiang, et al. "**Any-to-many voice conversion with location-relative sequence-to-sequence modeling.**" IEEE/ACM Transactions on Audio, Speech, and Language Processing 29 (2021): 1717-1728.. [[Paper]](https://arxiv.org/abs/2009.02725v3) [[Project]](https://github.com/liusongxiang/ppg-vc) 154 | 155 | :heavy_check_mark: - Neekhara, Paarth, et al. "**Expressive Neural Voice Cloning.**" *arXiv preprint arXiv:2102.00151(2021)*.[[Paper]](https://www.arxiv-vanity.com/papers/2102.00151/) 156 | 157 | :heavy_check_mark: - Cifka, Ondrej, et al. "**Self-Supervised VQ-VAE For One-Shot Music Style Transfer.**" *arXiv preprint arXiv:2102.05749(2021)*.[[Paper]](https://arxiv.org/abs/2102.05749) [[Project]](https://github.com/cifkao/ss-vq-vae) 158 | 159 | :heavy_check_mark: - Zhao, Shengkui, et al. "**Towards Natural and Controllable Cross-Lingual Voice Conversion Based on Neural TTS Model and Phonetic Posteriorgram.**"*arXiv preprint arXiv:2102.01991(2021)*.[[Paper]](https://www.arxiv-vanity.com/papers/2102.01991/) 160 | 161 | :heavy_check_mark: - H. Kameoka, T. Kaneko, K. Tanaka, and N. Hojo. "**StarGAN-VC: Non-parallel Many-to-Many Voice Conversion with Star Generative Adversarial Networks.**" *arXiv:1806.02169, June 2018* (SLT, 2018). [[Paper]](https://arxiv.org/abs/1806.02169) [[Project]](https://www.kecl.ntt.co.jp/people/kameoka.hirokazu/Demos/stargan-vc/) 162 | 163 | :heavy_check_mark: - J. Lorenzo-Trueba, J. Yamagishi, T. Toda, D. Saito, F. Villavicencio, T. Kinnunen, and Z. Ling. "**The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods.**" *Speaker Odyssey, 2018*. [[Paper]](https://arxiv.org/abs/1804.04262) [[Dataset]](https://datashare.ed.ac.uk/handle/10283/3061) 164 | 165 | :heavy_check_mark: - K. Kobayashi and T. Toda. "**sprocket: Open-Source Voice Conversion Software.**" *Speaker Odyssey, 2018.* [[Paper]](https://nuss.nagoya-u.ac.jp/s/h8YKnq6qxjjxtU3#pdfviewer) [[Project]](https://github.com/k2kobayashi/sprocket) [[Samples (zip)]](https://nuss.nagoya-u.ac.jp/login) 166 | 167 | :heavy_check_mark: - T. Kaneko and H. Kameoka. "**Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks.**" *arXiv:1711.11293, Nov. 2017 (EUSIPCO, 2018)*. [[Paper]](https://arxiv.org/abs/1711.11293) [[Project]](http://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/cyclegan-vc/index.html) 168 | 169 | :heavy_check_mark: - T. Kaneko, H. Kameoka, K. Tanaka, and N. Hojo. "**CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion.**" *ICASSP, 2019*. [[Paper]](https://arxiv.org/abs/1904.04631) [[Project]](http://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/cyclegan-vc2/index.html) [[github]](https://github.com/jackaduma/CycleGAN-VC2) 170 | 171 | :heavy_check_mark: - H. Kameoka, T. Kaneko, K. Tanaka, and N. Hojo. "**ACVAE-VC: Non-parallel Many-to-Many Voice Conversion with Auxiliary Classifier Variational Autoencoder.**" *arXiv:1808.05092, Aug. 2018. (IEEE/ACM Transactions on Audio, Speech, and Language Processing, May 2019)*. [[Paper]](https://arxiv.org/abs/1808.05092) [[Project]](http://www.kecl.ntt.co.jp/people/kameoka.hirokazu/Demos/acvae-vc/) 172 | 173 | :heavy_check_mark: - C. Hsu, H.-T. Hwang, Y.-C. Wu, Y. Tsao, and H.-M. Wang. "**Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks.**" *Interspeech, 2017*. [[Paper]](https://arxiv.org/abs/1704.00849) [[Project]](https://jeremycchsu.github.io/vc-vawgan/) 174 | 175 | :heavy_check_mark: - Kaneko, Takuhiro, et al. "**StarGAN-VC2: Rethinking conditional methods for StarGAN-based voice conversion.**" *arXiv preprint arXiv:1907.12279 (2019)*. [[Paper]](https://arxiv.org/abs/1907.12279) [[Project]](http://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/stargan-vc2/index.html) 176 | 177 | :heavy_check_mark: - Qian, Kaizhi, et al. "**Autovc: Zero-shot voice style transfer with only autoencoder loss.**" *arXiv preprint arXiv:1905.05879 (2019)*.[[Paper]](https://arxiv.org/pdf/1905.05879.pdf) [[Project]](https://github.com/auspicious3000/autovc) 178 | 179 | :heavy_check_mark: - Qian, Kaizhi, et al. "**Unsupervised speech decomposition via triple information bottleneck.**" *arXiv preprint arXiv:2004.11284 (2020)*. [[Paper]](https://arxiv.org/abs/2004.11284) [[Project]](https://auspicious3000.github.io/SpeechSplit-Demo/) 180 | 181 | :heavy_check_mark: - T. Toda, A. W Black, and K. Tokuda. "**Voice Conversion Based on Maximum Likelihood Estimation of Spectral Parameter Trajectory.**" *IEEE Trans. Audio Speech Lang. Process., 2007*. [[Paper]](https://ieeexplore.ieee.org/document/4317579?reload=true) 182 | 183 | :heavy_check_mark: - Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "**A neural algorithm of artistic style.**"*arXiv preprint arXiv:1508.06576(2015)*.[[Paper]](https://arxiv.org/abs/1508.06576)[[Project]](https://github.com/mazzzystar/randomCNN-voice-transfer) 184 | 185 | :heavy_check_mark: - K. Kobayashi, T. Toda, and S. Nakamura. "**F0 Transformation Techniques for Statistical Voice Conversion with Direct Waveform Modification with Spectral Differential.**" *SLT, 2016*. [[Paper]](https://ieeexplore.ieee.org/document/7846338) [[Project]](https://github.com/k2kobayashi/sprocket) 186 | 187 | :heavy_check_mark: - M. Morise, F. Yokomori, and K. Ozawa. "**WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time Applications.**" *IEICE Trans. Inf. Syst., 2016*. [[Paper]](https://www.jstage.jst.go.jp/article/transinf/E99.D/7/E99.D_2015EDP7457/_article) [[Project]](http://www.kki.yamanashi.ac.jp/~mmorise/world/english/index.html) 188 | 189 | :heavy_check_mark: - Wu, Da-Yi, and Yi-Hsuan Yang. "**Speech-to-Singing Conversion based on Boundary Equilibrium GAN.**"*arXiv preprint arXiv:2005.13835(2020)*.[[Paper]](https://arxiv.org/pdf/2005.13835.pdf) [[Project]](https://github.com/ericwudayi/speech2singing) 190 | 191 | :heavy_check_mark: - Sisman, Berrak, et al. "**An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning.**"*arXiv preprint arXiv:2008.03648(2020)*.[[Paper]](https://arxiv.org/pdf/2008.03648.pdf) 192 | 193 | :heavy_check_mark: - Peng, Yu-Huai, et al. "**The Academia Sinica Systems of Voice Conversion for VCC2020.**"*arXiv preprint arXiv:2010.02669(2020)*.[[Paper]](https://arxiv.org/abs/2010.02669) 194 | 195 | :heavy_check_mark: - Huang, Wen-Chin, et al. "**The Sequence-to-Sequence Baseline for the Voice Conversion Challenge 2020: Cascading ASR and TTS.**"*arXiv preprint arXiv:2010.02434(2020)*.[[Paper]](https://arxiv.org/abs/2010.02434) [[Project]](https://github.com/espnet/espnet) 196 | 197 | :heavy_check_mark: - Zhang, Mingyang, et al. "**Transfer Learning from Speech Synthesis to Voice Conversion with Non-Parallel Training Data.**"*arXiv preprint arXiv:2009.14399(2020)*.[[Paper]](https://arxiv.org/abs/2009.14399) 198 | 199 | :heavy_check_mark: - Wen-Chin Huang,et al."**The NU Voice Conversion System for the Voice Conversion Challenge 2020: On the Effectiveness of Sequence-to-sequence Models and Autoregressive Neural Vocoders.**"*arXiv preprint arXiv:2010.04446(2020)*.[[Paper]](https://arxiv.org/abs/2010.04446) 200 | 201 | :heavy_check_mark: - Oriol Barbany Mayor, Milos Cernak. "**FastVC: Fast Voice Conversion with non-parallel data.**" *arXiv preprint arXiv:2010.04185 (2020)*.[[Paper]](https://arxiv.org/abs/2010.04185) 202 | 203 | :heavy_check_mark: - Patrick Lumban Tobing,Yi-Chiao Wu,Tomoki Toda. "**Baseline System of Voice Conversion Challenge 2020 with Cyclic Variational Autoencoder and Parallel WaveGAN.**"*arXiv preprint arXiv:2010.04429(2020)*[[Paper]](https://arxiv.org/abs/2010.04429) 204 | 205 | :heavy_check_mark: - Kazuhiro Kobayashi Wen-Chin Huang Tomoki Toda . "**Non-parallel voice conversion based on vector-quantized variational autoencoder with adversarial learning**" 206 | 207 | :heavy_check_mark: - Yamamoto, Ryuichi, Eunwoo Song, and Jae-Min Kim. "**Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram.**"*ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020*. [[Paper]](https://arxiv.org/pdf/1910.11480.pdf) 208 | 209 | :heavy_check_mark: - K. Kobayashi, T. Toda, "**sprocket: Open-Source Voice Conversion Software.**" *Proc. Odyssey, pp. 203-210, June 2018*.[[Paper]](https://nuss.nagoya-u.ac.jp/s/h8YKnq6qxjjxtU3) 210 | 211 | :heavy_check_mark: - Yukarin. **Realtime Yukarin: an application for real-time voice conversion.**[[Project]](https://github.com/Hiroshiba/realtime-yukarin) 212 | 213 | :heavy_check_mark: - VQ-VAE for Acoustic Unit Discovery and Voice Conversion.[[Project]](https://github.com/bshall/ZeroSpeech) 214 | 215 | :heavy_check_mark: - autovc-implement: [[f0-autovc]](https://github.com/hrnoh/f0-autovc), [[AutoVC.pytorch]](https://github.com/peisuke/AutoVC.pytorch), [[autovc_v2]](https://github.com/casperwang/autovc_v2), [[AutoVC-WavRNN]](https://github.com/freenowill/AutoVC-WavRNN), [[AutoVC]](https://github.com/CODEJIN/AutoVC) 216 | 217 | :heavy_check_mark: - Lin, Yist Y., et al. "**FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention.**"*arXiv preprint arXiv:2010.14150(2020)*. [[Paper]](https://arxiv.org/abs/2010.14150) [[Project]](https://github.com/yistLin/FragmentVC) 218 | 219 | :heavy_check_mark: - Sun, Lifa, et al. "**Phonetic posteriorgrams for many-to-one voice conversion without parallel data training.**"*2016 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2016*.[[Paper]](https://ieeexplore.ieee.org/document/7552917) [[Project]](https://github.com/andabi/deep-voice-conversion) 220 | 221 | :heavy_check_mark: - Huang, Wen-Chin, et al. "**Unsupervised Representation Disentanglement Using Cross Domain Features and Adversarial Learning in Variational Autoencoder Based Voice Conversion.**"*IEEE Transactions on Emerging Topics in Computational Intelligence(2020)*. [[Paper]](https://ieeexplore.ieee.org/abstract/document/9057379) [[Project]](https://github.com/unilight/cdvae-vc) 222 | 223 | :heavy_check_mark: - Chou, Ju-chieh, et al. "**Multi-target voice conversion without parallel data by adversarially learning disentangled audio representations.**"*arXiv preprint arXiv:1804.02812(2018)*.[[Paper]](https://arxiv.org/pdf/1804.02812.pdf) [[Project]](https://github.com/BogiHsu/Voice-Conversion) 224 | 225 | :heavy_check_mark: - Grinstein, Eric, et al. "**Audio style transfer.**"*2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018*.[[Paper]](https://hal.archives-ouvertes.fr/hal-01626389/document) [[Project]](https://github.com/inzva/Audio-Style-Transfer) [[HomePage]](https://egrinstein.github.io/2017/10/25/ast.html) 226 | 227 | :heavy_check_mark: - Li, Tingle, et al. "**CVC: Contrastive Learning for Non-parallel Voice Conversion.**"*arXiv preprint arXiv:2011.00782(2020)*.[[Paper]](https://arxiv.org/abs/2011.00782) [[Project]](https://github.com/Tinglok/CVC) 228 | 229 | :heavy_check_mark: - Huang, Wen-Chin, et al. "**Any-to-One Sequence-to-Sequence Voice Conversion using Self-Supervised Discrete Speech Representations.**"*arXiv preprint arXiv:2010.12231(2020)*.[[Paper]](https://arxiv.org/pdf/2010.12231.pdf) 230 | 231 | :heavy_check_mark: - Li, Zhonghao, et al. "**PPG-based singing voice conversion with adversarial representation learning.**"*arXiv preprint arXiv:2010.14804(2020)*.[[Paper]](https://arxiv.org/pdf/2010.14804.pdf) 232 | 233 | :heavy_check_mark: - Zhang, Jing-Xuan, Zhen-Hua Ling, and Li-Rong Dai. "**Non-parallel sequence-to-sequence voice conversion with disentangled linguistic and speaker representations.**"*IEEE/ACM Transactions on Audio, Speech, and Language Processing28 (2019): 540-552*.[[Paper]](https://arxiv.org/pdf/1906.10508.pdf) [[Project]](https://github.com/jxzhanggg/nonparaSeq2seqVC_code) 234 | 235 | :heavy_check_mark: - Ding, Shaojin, Guanlong Zhao, and Ricardo Gutierrez-Osuna. "**Improving the Speaker Identity of Non-Parallel Many-to-Many Voice Conversion with Adversarial Speaker Recognition.**"*Proc. Interspeech 2020(2020): 776-780*.[[Paper]](http://www.interspeech2020.org/uploadfile/pdf/Mon-2-7-2.pdf) [[Project]](https://github.com/shaojinding/Adversarial-Many-to-Many-VC) 236 | 237 | :heavy_check_mark: - Chang, Che-Jui. "**Transfer Learning from Monolingual ASR to Transcription-free Cross-lingual Voice Conversion.**"*arXiv preprint arXiv:2009.14668(2020)*.[[Paper]](https://arxiv.org/ftp/arxiv/papers/2009/2009.14668.pdf) [[Project]](https://github.com/cjerry1243/TransferLearning-CLVC) 238 | 239 | :heavy_check_mark: - Guo, Haohan, et al. "**Phonetic Posteriorgrams based Many-to-Many Singing Voice Conversion via Adversarial Training.**"*arXiv preprint arXiv:2012.01837(2020)*.[[Paper]](https://arxiv.org/pdf/2012.01837.pdf) [[Project]](https://github.com/hhguo/EA-SVC) 240 | 241 | :heavy_check_mark: - Wang, Zhichao, et al. "**Accent and Speaker Disentanglement in Many-to-many Voice Conversion.**"*arXiv preprint arXiv:2011.08609(2020)*.[[Paper]](https://arxiv.org/pdf/2011.08609.pdf) [[Project]](https://kerwinchao.github.io/AccentVoicejointConversion.github.io/) 242 | 243 | :heavy_check_mark: - Zhao, Guanlong, and Ricardo Gutierrez-Osuna. "**Using phonetic posteriorgram based frame pairing for segmental accent conversion.**"*IEEE/ACM Transactions on Audio, Speech, and Language Processing27.10 (2019): 1649-1660*.[[Paper]](https://ieeexplore.ieee.org/document/8755490) 244 | 245 | :heavy_check_mark: - Zhou, Kun, et al. "**Seen and unseen emotional style transfer for voice conversion with a new emotional speech dataset.**"*arXiv preprint arXiv:2010.14794(2020)*.[[Paper]](https://arxiv.org/pdf/2010.14794.pdf) [[Project]](https://kunzhou9646.github.io/controllable-evc/) 246 | 247 | :heavy_check_mark: - Wang, Jie, et al. "**Adversarially learning disentangled speech representations for robust multi-factor voice conversion.**"*arXiv preprint arXiv:2102.00184(2021)*.[[Paper]](https://arxiv.org/pdf/2102.00184.pdf) 248 | 249 | :heavy_check_mark: - Rebryk, Yurii, and Stanislav Beliaev. "**ConVoice: Real-Time Zero-Shot Voice Style Transfer with Convolutional Network.**"*arXiv preprint arXiv:2005.07815(2020)*.[[Paper]](https://www.dropbox.com/s/h781sva0dv177ot/ConVoice.pdf?dl=0) 250 | 251 | :heavy_check_mark: - Serrà, Joan, Santiago Pascual, and Carlos Segura. "**Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion.**"*arXiv preprint arXiv:1906.00794(2019)*.[[Paper]](https://www.dropbox.com/s/6bovin589qr78l8/Blow.pdf?dl=0) 252 | 253 | :heavy_check_mark: - **Voice conversion using deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks**(2015), *Lifa Sun et al*. [[Paper]](https://ieeexplore.ieee.org/document/7178896) 254 | 255 | :heavy_check_mark: - **Phonetic posteriorgrams for many-to-one voice conversion without parallel data training**(2016), *Lifa Sun et al*. [[Paper]](https://ieeexplore.ieee.org/document/7552917) 256 | 257 | 258 | 259 | ### Music Modelling 260 | 261 | - **Onsets and Frames: Dual-Objective Piano Transcription**(2017), Curtis Hawthorne et al. [[Paper]](https://arxiv.org/abs/1710.11153) 262 | 263 | - **ByteSing- A Chinese Singing Voice Synthesis System Using Duration Allocated Encoder-Decoder Acoustic Models and WaveRNN Vocoders**(2020), Yu Gu et al. [[Paper]](https://arxiv.org/pdf/2004.11012) 264 | 265 | - **HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis**(2020), Jiawei Chen et al. [[Paper]](https://arxiv.org/pdf/2009.01776) 266 | 267 | - **Jukebox: A Generative Model for Music**(2020), Prafulla Dhariwal et al. [[Paper]](https://arxiv.org/pdf/2005.00341) 268 | 269 | - **PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components**(2021), Yukiya Hono et al. [[Paper]](https://arxiv.org/pdf/2102.07786) 270 | 271 | 272 | ### Singing Voice Conversion 273 | 274 | - Lu, Junchen, et al. "**VAW-GAN for Singing Voice Conversion with Non-parallel Training Data.**" *2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 2020*.[[Paper]](https://arxiv.org/pdf/2008.03992.pdf) [[Project]](https://github.com/KunZhou9646/Singing-Voice-Conversion-with-conditional-VAW-GAN) 275 | 276 | - SingingVoiceConversion[[Project]](https://github.com/jshong0907/SingingVoiceConversion), Singing-Voice-Conversion[[Project]](https://github.com/solalala-12/Singing-Voice-Conversion) 277 | 278 | - Mor, Noam, et al. "**A universal music translation network.**" *arXiv preprint arXiv:1805.07848(2018)*.[[Paper]](https://arxiv.org/abs/1805.07848) [[Project]](https://github.com/facebookresearch/music-translation) 279 | 280 | - Guo, Haohan, et al. "**Phonetic Posteriorgrams based Many-to-Many Singing Voice Conversion via Adversarial Training.**" *arXiv preprint arXiv:2012.01837(2020)*.[[Paper]](https://arxiv.org/abs/2012.01837) [[Project]](https://github.com/hhguo/EA-SVC) 281 | 282 | - Takahashi, Naoya, Mayank Kumar Singh, and Yuki Mitsufuji. "**Hierarchical disentangled representation learning for singing voice conversion.**" *arXiv preprint arXiv:2101.06842(2021)*.[[Paper]](https://arxiv.org/pdf/2101.06842.pdf) 283 | 284 | - Basak, Sakya, et al. "**End-to-end lyrics Recognition with Voice to Singing Style Transfer.**" *arXiv preprint arXiv:2102.08575(2021).*[[Paper]](https://arxiv.org/pdf/2102.08575.pdf) 285 | 286 | - Sankaran, Shreeviknesh, Sukavanan Nanjundan, and G. Paavai Anand. "**Anyone GAN Sing.**" *arXiv preprint arXiv:2102.11058(2021).*[[Paper]](https://arxiv.org/pdf/2102.11058.pdf) 287 | - Tae, Jaesung, Hyeongju Kim, and Younggun Lee. "MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis." *arXiv preprint arXiv:2106.07886 (2021).*[[Paper]](https://arxiv.org/pdf/2106.07886.pdf) [[Projects]](https://github.com/CODEJIN/MLPSinger) 288 | 289 | 290 | ### Interesting papers 291 | 292 | - **The Reversible Residual Network: Backpropagation Without Storing Activations**(2017), Aidan N. Gomez et al. [[Paper]](https://arxiv.org/pdf/1707.04585) 293 | 294 | - **FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow**(2019), Xuezhe Ma et al. [[Paper]](https://arxiv.org/pdf/1909.02480) 295 | 296 | - **Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks**(2019), Santiago Pascual et al. [[Paper]](https://arxiv.org/pdf/1904.03416.pdf) 297 | 298 | - **Self-supervised audio representation learning for mobile devices**(2019), Marco Tagliasacchi et al. [[Paper]](https://arxiv.org/pdf/1905.11796.pdf) 299 | 300 | - **SinGAN: Learning a Generative Model from a Single Natural Image**(2019), Tamar Rott Shaham et al. [[Paper]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Shaham_SinGAN_Learning_a_Generative_Model_From_a_Single_Natural_Image_ICCV_2019_paper.pdf) 301 | 302 | - **Audio2Face: Generating Speech/Face Animation from Single Audio with Attention-Based Bidirectional LSTM Networks**(2019), Guanzhong Tian et al. [[Paper]](https://arxiv.org/pdf/1905.11142) 303 | 304 | - **Attention is Not Only a Weight: Analyzing Transformers with Vector Norms**(2020), Goro Kobayashi et al. [[Paper]](https://arxiv.org/pdf/2004.10102) 305 | - **Speak Like a Dog: Human to Non-human creature Voice Conversion**(2022), Kohei Suzuki et al. [[Paper]](https://arxiv.org/abs/2206.04780) 306 | 307 | 308 | ## Contact Me 309 | If you have any questions, Contact Me ，thanks 310 | --------------------------------------------------------------------------------