Joint Modeling of Text, Audio, and 3D Motion Using RapVerse | HackerNoon

Table of Links

Abstract and 1. Introduction

2. Related Work

   2.1 Text to Vocal Generation

   2.2 Text to Motion Generation

   2.3 Audio to Motion Generation

3. RapVerse Dataset

   3.1 Rap-Vocal Subset

   3.2 Rap-Motion Subset

4. Method

   4.1 Problem Formulation

   4.2 Motion VQ-VAE Tokenizer

   4.3 Vocal2unit Audio Tokenizer

   4.4 General Auto-regressive Modeling

5. Experiments

   5.1 Experimental Setup

   5.2 Main Results Analysis and 5.3 Ablation Study

6. Conclusion and References

A. Appendix

6 Conclusion

In this work, we present a new framework for the simultaneous generation of 3D whole-body motions and singing vocals, directly from textual lyrics. To address this challenging task, we first collect RapVerse, a large dataset containing synchronous rap vocals, alongside lyrics and 3D whole-body motions. Utilizing RapVerse, we demonstrate that simply scaling autoregressive transformers across language, audio, and motion yields a coherent generation of singing vocals and 3D holistic human motions. We anticipate that this work will inspire novel avenues in the joint modeling of text, audio, and motion.

Limitations and Future Works. One limitation of RapVerse is that it is currently constrained to the rap music generation, excluding other music genres. However, we want to emphasize that our method is a general framework that could be flexibly utilized in other scenarios for joint audio and motion generation if provided with the datasets. Another important future direction resides in multi-performer audio and motion generation, which could be utilized in contemporary music performances such as virtual live bands.

References

[1] Andrea Agostinelli, Timo I Denk, Zalán Borsos, Jesse Engel, Mauro Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen, Adam Roberts, Marco Tagliasacchi, et al. Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325, 2023.

[2] Chaitanya Ahuja and Louis-Philippe Morency. Language2pose: Natural language grounded pose forecasting. In 2019 International Conference on 3D Vision (3DV), pages 719–728. IEEE, 2019.

[3] Zhe Cao, Tomas Simon, Shih-En Wei, and Yaser Sheikh. Realtime multi-person 2d pose estimation using part affinity fields. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7291–7299, 2017.

[4] Xin Chen, Biao Jiang, Wen Liu, Zilong Huang, Bin Fu, Tao Chen, and Gang Yu. Executing your commands via motion diffusion in latent space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18000–18010, 2023.

[5] Daniel Cudeiro, Timo Bolkart, Cassidy Laidlaw, Anurag Ranjan, and Michael J Black. Capture, learning, and synthesis of 3d speaking styles. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10101–10111, 2019.

[6] Prafulla Dhariwal, Heewoo Jun, Christine Payne, Jong Wook Kim, Alec Radford, and Ilya Sutskever. Jukebox: A generative model for music. arXiv preprint arXiv:2005.00341, 2020.

[7] Jeff Donahue, Sander Dieleman, Mikołaj Binkowski, Erich Elsen, and Karen Simonyan. End-to-end ´ adversarial text-to-speech. arXiv preprint arXiv:2006.03575, 2020.

[8] Zhiyan Duan, Haotian Fang, Bo Li, Khe Chai Sim, and Ye Wang. The nus sung and spoken lyrics corpus: A quantitative comparison of singing and speech. In 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, pages 1–9. IEEE, 2013.

[9] Gabriele Fanelli, Juergen Gall, Harald Romsdorfer, Thibaut Weise, and Luc Van Gool. A 3-d audio-visual corpus of affective communication. IEEE Transactions on Multimedia, 12(6):591–598, 2010.

[10] Ylva Ferstl and Rachel McDonnell. Investigating the use of recurrent motion modelling for speech gesture generation. In Proceedings of the 18th International Conference on Intelligent Virtual Agents, pages 93–98, 2018.

[11] Anindita Ghosh, Noshaba Cheema, Cennet Oguz, Christian Theobalt, and Philipp Slusallek. Synthesis of compositional animations from textual descriptions. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1396–1406, 2021.

[12] Shiry Ginosar, Amir Bar, Gefen Kohavi, Caroline Chan, Andrew Owens, and Jitendra Malik. Learning individual styles of conversational gesture. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3497–3506, 2019.

[13] Chuan Guo, Shihao Zou, Xinxin Zuo, Sen Wang, Wei Ji, Xingyu Li, and Li Cheng. Generating diverse and natural 3d human motions from text. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5152–5161, 2022.

[14] Chuan Guo, Xinxin Zuo, Sen Wang, and Li Cheng. Tm2t: Stochastic and tokenized modeling for the reciprocal generation of 3d human motions and texts. In European Conference on Computer Vision, pages 580–597. Springer, 2022.

[15] Ikhsanul Habibie, Weipeng Xu, Dushyant Mehta, Lingjie Liu, Hans-Peter Seidel, Gerard Pons-Moll, Mohamed Elgharib, and Christian Theobalt. Learning speech-driven 3d conversational gestures from video. In Proceedings of the 21st ACM International Conference on Intelligent Virtual Agents, pages 101–108, 2021.

[16] Jinzheng He, Jinglin Liu, Zhenhui Ye, Rongjie Huang, Chenye Cui, Huadai Liu, and Zhou Zhao. Rmssinger: Realistic-music-score based singing voice synthesis. arXiv preprint arXiv:2305.10686, 2023.

[17] Georg Heigold, Ignacio Moreno, Samy Bengio, and Noam Shazeer. End-to-end text-dependent speaker verification. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 5115–5119. IEEE, 2016.

[18] Romain Hennequin, Anis Khlif, Felix Voituret, and Manuel Moussallam. Spleeter: a fast and efficient music source separation tool with pre-trained models. Journal of Open Source Software, 5(50):2154, 2020.

[19] Romain Hennequin, Anis Khlif, Felix Voituret, and Manuel Moussallam. Spleeter: a fast and efficient music source separation tool with pre-trained models. Journal of Open Source Software, 5(50):2154, 2020. Deezer Research.

[20] Wei-Ning Hsu, Yao-Hung Hubert Tsai, Benjamin Bolte, Ruslan Salakhutdinov, and Abdelrahman Mohamed. Hubert: How much can a bad teacher benefit asr pre-training? In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 6533–6537. IEEE, 2021.

[21] Qingqing Huang, Daniel S Park, Tao Wang, Timo I Denk, Andy Ly, Nanxin Chen, Zhengdong Zhang, Zhishuai Zhang, Jiahui Yu, Christian Frank, et al. Noise2music: Text-conditioned music generation with diffusion models. arXiv preprint arXiv:2302.03917, 2023.

[22] Rongjie Huang, Feiyang Chen, Yi Ren, Jinglin Liu, Chenye Cui, and Zhou Zhao. Multi-singer: Fast multi-singer singing voice vocoder with a large-scale corpus. In Proceedings of the 29th ACM International Conference on Multimedia, pages 3945–3954, 2021.

[23] Biao Jiang, Xin Chen, Wen Liu, Jingyi Yu, Gang Yu, and Tao Chen. Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems, 36, 2024.

[24] Kavita Kasi and Stephen A Zahorian. Yet another algorithm for pitch tracking. In 2002 ieee international conference on acoustics, speech, and signal processing, volume 1, pages I–361. IEEE, 2002.

[25] Jihoon Kim, Jiseob Kim, and Sungjoon Choi. Flame: Free-form language-based motion synthesis & editing. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 8255–8263, 2023.

[26] Sungjae Kim, Yewon Kim, Jewoo Jun, and Injung Kim. Muse-svs: Multi-singer emotional singing voice synthesizer that controls emotional intensity. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023.

[27] Kushal Lakhotia, Eugene Kharitonov, Wei-Ning Hsu, Yossi Adi, Adam Polyak, Benjamin Bolte, Tu-Anh Nguyen, Jade Copet, Alexei Baevski, Abdelrahman Mohamed, et al. On generative spoken language modeling from raw audio. Transactions of the Association for Computational Linguistics, 9:1336–1354, 2021.

[28] George Lakoff and Mark Johnson. Metaphors We Live By. University of Chicago Press, 2003 edition, 1980. First published January 1, 1980.

[29] Ruilong Li, Shan Yang, David A Ross, and Angjoo Kanazawa. Ai choreographer: Music conditioned 3d dance generation with aist++. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 13401–13412, 2021.

[30] Jing Lin, Ailing Zeng, Shunlin Lu, Yuanhao Cai, Ruimao Zhang, Haoqian Wang, and Lei Zhang. Motion-x: A large-scale 3d expressive whole-body human motion dataset. Advances in Neural Information Processing Systems, 36, 2024.

[31] Haiyang Liu, Zihao Zhu, Giorgio Becherini, Yichen Peng, Mingyang Su, You Zhou, Naoya Iwamoto, Bo Zheng, and Michael J Black. Emage: Towards unified holistic co-speech gesture generation via masked audio gesture modeling. arXiv preprint arXiv:2401.00374, 2023.

[32] Jinglin Liu, Chengxi Li, Yi Ren, Feiyang Chen, and Zhou Zhao. Diffsinger: Singing voice synthesis via shallow diffusion mechanism. In Proceedings of the AAAI conference on artificial intelligence, volume 36, pages 11020–11028, 2022.

[33] Shuhong Lu, Youngwoo Yoon, and Andrew Feng. Co-speech gesture synthesis using discrete gesture token learning. arXiv preprint arXiv:2303.12822, 2023.

[34] Shunlin Lu, Ling-Hao Chen, Ailing Zeng, Jing Lin, Ruimao Zhang, Lei Zhang, and Heung-Yeung Shum. Humantomato: Text-aligned whole-body motion generation. arXiv preprint arXiv:2310.12978, 2023.

[35] Naureen Mahmood, Nima Ghorbani, Nikolaus F Troje, Gerard Pons-Moll, and Michael J Black. Amass: Archive of motion capture as surface shapes. In Proceedings of the IEEE/CVF international conference on computer vision, pages 5442–5451, 2019.

[36] Brian McFee, Colin Raffel, Dawen Liang, Daniel PW Ellis, Matt McVicar, Eric Battenberg, and Oriol Nieto. librosa: Audio and music signal analysis in python. In SciPy, pages 18–24, 2015.

[37] Dongchan Min, Dong Bok Lee, Eunho Yang, and Sung Ju Hwang. Meta-stylespeech: Multi-speaker adaptive text-to-speech generation. In International Conference on Machine Learning, pages 7748–7759. PMLR, 2021.

[38] Tomohiro Nakatani, Shigeaki Amano, Toshio Irino, Kentaro Ishizuka, and Tadahisa Kondo. A method for fundamental frequency estimation and voicing decision: Application to infant utterances recorded in real acoustical environments. Speech Communication, 50(3):203–214, 2008.

[39] Itsuki Ogawa and Masanori Morise. Tohoku kiritan singing database: A singing database for statistical parametric singing synthesis using japanese pop songs. Acoustical Science and Technology, 42(3):140–145, 2021.

[40] Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, and Koray Kavukcuoglu. Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499, 2016.

[41] Vassil Panayotov, Guoguo Chen, Daniel Povey, and Sanjeev Khudanpur. Librispeech: an asr corpus based on public domain audio books. In 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pages 5206–5210. IEEE, 2015.

[42] Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed AA Osman, Dimitrios Tzionas, and Michael J Black. Expressive body capture: 3d hands, face, and body from a single image. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10975–10985, 2019.

[43] Mathis Petrovich, Michael J Black, and Gül Varol. Temos: Generating diverse human motions from textual descriptions. In European Conference on Computer Vision, pages 480–497. Springer, 2022.

[44] Matthias Plappert, Christian Mandery, and Tamim Asfour. The kit motion-language dataset. Big data, 4(4):236–252, 2016.

[45] Adam Polyak, Yossi Adi, Jade Copet, Eugene Kharitonov, Kushal Lakhotia, Wei-Ning Hsu, Abdelrahman Mohamed, and Emmanuel Dupoux. Speech resynthesis from discrete disentangled self-supervised representations. arXiv preprint arXiv:2104.00355, 2021.

[46] Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. Robust speech recognition via large-scale weak supervision, 2022.

[47] Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning, pages 28492–28518. PMLR, 2023.

[48] Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, 21(140):1–67, 2020.

[49] Ali Razavi, Aaron Van den Oord, and Oriol Vinyals. Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems, 32, 2019.

[50] Joseph Redmon and Ali Farhadi. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767, 2018.

[51] Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. Fastspeech 2: Fast and high-quality end-to-end text to speech. arXiv preprint arXiv:2006.04558, 2020.

[52] Yi Ren, Yangjun Ruan, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. Fastspeech: Fast, robust and controllable text to speech. Advances in neural information processing systems, 32, 2019.

[53] Yi Ren, Xu Tan, Tao Qin, Jian Luan, Zhou Zhao, and Tie-Yan Liu. Deepsinger: Singing voice synthesis with data mined from the web. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 1979–1989, 2020.

[54] Flavio Schneider, Ojasv Kamal, Zhijing Jin, and Bernhard Schölkopf. Moˆ usai: Text-to-music generation with long-context latent diffusion. arXiv preprint arXiv:2301.11757, 2023.

[55] Bidisha Sharma, Xiaoxue Gao, Karthika Vijayan, Xiaohai Tian, and Haizhou Li. Nhss: A speech and singing parallel database. Speech Communication, 133:9–22, 2021.

[56] Shuai Shen, Wenliang Zhao, Zibin Meng, Wanhua Li, Zheng Zhu, Jie Zhou, and Jiwen Lu. Difftalk: Crafting diffusion models for generalized talking head synthesis. arXiv preprint arXiv:2301.03786, 2023.

[57] Kenta Takeuchi, Souichirou Kubota, Keisuke Suzuki, Dai Hasegawa, and Hiroshi Sakuta. Creating a gesture-speech dataset for speech-based automatic gesture generation. In HCI International 2017–Posters’ Extended Abstracts: 19th International Conference, HCI International 2017, Vancouver, BC, Canada, July 9–14, 2017, Proceedings, Part I 19, pages 198–202. Springer, 2017.

[58] Hiroki Tamaru, Shinnosuke Takamichi, Naoko Tanji, and Hiroshi Saruwatari. Jvs-music: Japanese multispeaker singing-voice corpus. arXiv preprint arXiv:2001.07044, 2020.

[59] Sarah Taylor, Taehwan Kim, Yisong Yue, Moshe Mahler, James Krahe, Anastasio Garcia Rodriguez, Jessica Hodgins, and Iain Matthews. A deep learning approach for generalized speech animation. ACM Transactions On Graphics (TOG), 36(4):1–11, 2017.

[60] Zachary Teed and Jia Deng. Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16, pages 402–419. Springer, 2020.

[61] Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, and Amit H Bermano. Human motion diffusion model. arXiv preprint arXiv:2209.14916, 2022.

[62] Jean-Marc Valin and Jan Skoglund. Lpcnet: Improving neural speech synthesis through linear prediction. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 5891–5895. IEEE, 2019.

[63] Aaron Van Den Oord, Oriol Vinyals, et al. Neural discrete representation learning. Advances in neural information processing systems, 30, 2017.

[64] Yu Wang, Xinsheng Wang, Pengcheng Zhu, Jie Wu, Hanzhao Li, Heyang Xue, Yongmao Zhang, Lei Xie, and Mengxiao Bi. Opencpop: A high-quality open source chinese popular song corpus for singing voice synthesis. arXiv preprint arXiv:2201.07429, 2022.

[65] Cheng-hsin Wuu, Ningyuan Zheng, Scott Ardisson, Rohan Bali, Danielle Belko, Eric Brockmeyer, Lucas Evans, Timothy Godisart, Hyowon Ha, Xuhua Huang, et al. Multiface: A dataset for neural face rendering. arXiv preprint arXiv:2207.11243, 2022.

[66] Jinbo Xing, Menghan Xia, Yuechen Zhang, Xiaodong Cun, Jue Wang, and Tien-Tsin Wong. Codetalker: Speech-driven 3d facial animation with discrete motion prior. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12780–12790, 2023.

[67] Geng Yang, Shan Yang, Kai Liu, Peng Fang, Wei Chen, and Lei Xie. Multi-band melgan: Faster waveform generation for high-quality text-to-speech. In 2021 IEEE Spoken Language Technology Workshop (SLT), pages 492–498. IEEE, 2021.

[68] Hongwei Yi, Hualin Liang, Yifei Liu, Qiong Cao, Yandong Wen, Timo Bolkart, Dacheng Tao, and Michael J Black. Generating holistic 3d human motion from speech. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 469–480, 2023.

[69] Jianrong Zhang, Yangsong Zhang, Xiaodong Cun, Shaoli Huang, Yong Zhang, Hongwei Zhao, Hongtao Lu, and Xi Shen. T2m-gpt: Generating human motion from textual descriptions with discrete representations. arXiv preprint arXiv:2301.06052, 2023.

[70] Lichao Zhang, Ruiqi Li, Shoutong Wang, Liqun Deng, Jinglin Liu, Yi Ren, Jinzheng He, Rongjie Huang, Jieming Zhu, Xiao Chen, et al. M4singer: A multi-style, multi-singer and musical score provided mandarin singing corpus. Advances in Neural Information Processing Systems, 35:6914–6926, 2022.

[71] Mingyuan Zhang, Zhongang Cai, Liang Pan, Fangzhou Hong, Xinying Guo, Lei Yang, and Ziwei Liu. Motiondiffuse: Text-driven human motion generation with diffusion model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024.

[72] Wenxuan Zhang, Xiaodong Cun, Xuan Wang, Yong Zhang, Xi Shen, Yu Guo, Ying Shan, and Fei Wang. Sadtalker: Learning realistic 3d motion coefficients for stylized audio-driven single image talking face animation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8652–8661, 2023.

[73] Yu Zhang, Rongjie Huang, Ruiqi Li, JinZheng He, Yan Xia, Feiyang Chen, Xinyu Duan, Baoxing Huai, and Zhou Zhao. Stylesinger: Style transfer for out-of-domain singing voice synthesis. arXiv preprint arXiv:2312.10741, 2023.

[74] Zewang Zhang, Yibin Zheng, Xinhui Li, and Li Lu. Wesinger: Data-augmented singing voice synthesis with auxiliary losses. arXiv preprint arXiv:2203.10750, 2022.