Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Efficient Parallel Audio Generation using Group Masked Language Modeling (2401.01099v1)

Published 2 Jan 2024 in eess.AS, cs.AI, and cs.LG

Abstract: We present a fast and high-quality codec LLM for parallel audio generation. While SoundStorm, a state-of-the-art parallel audio generation model, accelerates inference speed compared to autoregressive models, it still suffers from slow inference due to iterative sampling. To resolve this problem, we propose Group-Masked LLMing~(G-MLM) and Group Iterative Parallel Decoding~(G-IPD) for efficient parallel audio generation. Both the training and sampling schemes enable the model to synthesize high-quality audio with a small number of iterations by effectively modeling the group-wise conditional dependencies. In addition, our model employs a cross-attention-based architecture to capture the speaker style of the prompt voice and improves computational efficiency. Experimental results demonstrate that our proposed model outperforms the baselines in prompt-based audio generation.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. A. Défossez, J. Copet, G. Synnaeve, and Y. Adi, “High fidelity neural audio compression,” arXiv preprint arXiv:2210.13438, 2022.
  2. N. Zeghidour, A. Luebs, A. Omran, J. Skoglund, and M. Tagliasacchi, “Soundstream: An end-to-end neural audio codec,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 30, pp. 495–507, 2021.
  3. T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al., “Language models are few-shot learners,” Advances in neural information processing systems, vol. 33, pp. 1877–1901, 2020.
  4. H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozière, N. Goyal, E. Hambro, F. Azhar et al., “Llama: Open and efficient foundation language models,” arXiv preprint arXiv:2302.13971, 2023.
  5. A. v. d. Oord, S. Dieleman, H. Zen, K. Simonyan, O. Vinyals, A. Graves, N. Kalchbrenner, A. Senior, and K. Kavukcuoglu, “Wavenet: A generative model for raw audio,” arXiv preprint arXiv:1609.03499, 2016.
  6. J. Kong, J. Kim, and J. Bae, “Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis,” Advances in Neural Information Processing Systems, vol. 33, pp. 17 022–17 033, 2020.
  7. Z. Kong, W. Ping, J. Huang, K. Zhao, and B. Catanzaro, “Diffwave: A versatile diffusion model for audio synthesis,” in International Conference on Learning Representations, 2020.
  8. Z. Borsos, R. Marinier, D. Vincent, E. Kharitonov, O. Pietquin, M. Sharifi, D. Roblek, O. Teboul, D. Grangier, M. Tagliasacchi et al., “Audiolm: a language modeling approach to audio generation,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023.
  9. C. Wang, S. Chen, Y. Wu, Z. Zhang, L. Zhou, S. Liu, Z. Chen, Y. Liu, H. Wang, J. Li et al., “Neural codec language models are zero-shot text to speech synthesizers,” arXiv preprint arXiv:2301.02111, 2023.
  10. E. Kharitonov, D. Vincent, Z. Borsos, R. Marinier, S. Girgin, O. Pietquin, M. Sharifi, M. Tagliasacchi, and N. Zeghidour, “Speak, read and prompt: High-fidelity text-to-speech with minimal supervision,” arXiv preprint arXiv:2302.03540, 2023.
  11. Z. Borsos, M. Sharifi, D. Vincent, E. Kharitonov, N. Zeghidour, and M. Tagliasacchi, “Soundstorm: Efficient parallel audio generation,” arXiv preprint arXiv:2305.09636, 2023.
  12. H. F. Garcia, P. Seetharaman, R. Kumar, and B. Pardo, “Vampnet: Music generation via masked acoustic token modeling,” arXiv preprint arXiv:2307.04686, 2023.
  13. J. Copet, F. Kreuk, I. Gat, T. Remez, D. Kant, G. Synnaeve, Y. Adi, and A. Défossez, “Simple and controllable music generation,” arXiv preprint arXiv:2306.05284, 2023.
  14. K. Shen, Z. Ju, X. Tan, Y. Liu, Y. Leng, L. He, T. Qin, S. Zhao, and J. Bian, “Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers,” arXiv preprint arXiv:2304.09116, 2023.
  15. G. L. Lan, V. Nagaraja, E. Chang, D. Kant, Z. Ni, Y. Shi, F. Iandola, and V. Chandra, “Stack-and-delay: a new codebook pattern for music generation,” arXiv preprint arXiv:2309.08804, 2023.
  16. J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” Advances in neural information processing systems, vol. 33, pp. 6840–6851, 2020.
  17. D. Yang, S. Liu, R. Huang, J. Tian, C. Weng, and Y. Zou, “Hifi-codec: Group-residual vector quantization for high fidelity audio codec,” arXiv preprint arXiv:2305.02765, 2023.
  18. A. Baevski, Y. Zhou, A. Mohamed, and M. Auli, “wav2vec 2.0: A framework for self-supervised learning of speech representations,” Advances in neural information processing systems, vol. 33, pp. 12 449–12 460, 2020.
  19. A. Van Den Oord, O. Vinyals et al., “Neural discrete representation learning,” Advances in neural information processing systems, vol. 30, 2017.
  20. Y.-A. Chung, Y. Zhang, W. Han, C.-C. Chiu, J. Qin, R. Pang, and Y. Wu, “W2v-bert: Combining contrastive learning and masked language modeling for self-supervised speech pre-training,” in 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).   IEEE, 2021, pp. 244–250.
  21. A. Gulati, J. Qin, C.-C. Chiu, N. Parmar, Y. Zhang, J. Yu, W. Han, S. Wang, Z. Zhang, Y. Wu, and R. Pang, “Conformer: Convolution-augmented Transformer for Speech Recognition,” in Proc. Interspeech 2020, 2020, pp. 5036–5040.
  22. H. Chang, H. Zhang, L. Jiang, C. Liu, and W. T. Freeman, “Maskgit: Masked generative image transformer,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11 315–11 325.
  23. A. Baevski, W.-N. Hsu, A. Conneau, and M. Auli, “Unsupervised speech recognition,” Advances in Neural Information Processing Systems, vol. 34, pp. 27 826–27 839, 2021.
  24. M. Kim, M. Jeong, B. J. Choi, S. Ahn, J. Y. Lee, and N. S. Kim, “Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus,” in Proc. Interspeech 2022, 2022, pp. 788–792.
  25. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), J. Burstein, C. Doran, and T. Solorio, Eds.   Minneapolis, Minnesota: Association for Computational Linguistics, Jun. 2019, pp. 4171–4186. [Online]. Available: https://aclanthology.org/N19-1423
  26. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
  27. H. Zen, V. Dang, R. Clark, Y. Zhang, R. J. Weiss, Y. Jia, Z. Chen, and Y. Wu, “LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech,” in Proc. Interspeech 2019, 2019, pp. 1526–1530.
  28. A. Babu, C. Wang, A. Tjandra, K. Lakhotia, Q. Xu, N. Goyal, K. Singh, P. von Platen, Y. Saraf, J. Pino et al., “Xls-r: Self-supervised cross-lingual speech representation learning at scale,” arXiv preprint arXiv:2111.09296, 2021.
  29. J. Kim, J. Kong, and J. Son, “Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,” in International Conference on Machine Learning.   PMLR, 2021, pp. 5530–5540.
  30. B. Desplanques, J. Thienpondt, and K. Demuynck, “ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification,” in Proc. Interspeech 2020, 2020, pp. 3830–3834.
  31. A. Radford, J. W. Kim, T. Xu, G. Brockman, C. McLeavey, and I. Sutskever, “Robust speech recognition via large-scale weak supervision,” in International Conference on Machine Learning.   PMLR, 2023, pp. 28 492–28 518.
  32. S. Chen, C. Wang, Z. Chen, Y. Wu, S. Liu, Z. Chen, J. Li, N. Kanda, T. Yoshioka, X. Xiao et al., “Wavlm: Large-scale self-supervised pre-training for full stack speech processing,” IEEE Journal of Selected Topics in Signal Processing, vol. 16, no. 6, pp. 1505–1518, 2022.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Myeonghun Jeong (12 papers)
  2. Minchan Kim (18 papers)
  3. Joun Yeop Lee (10 papers)
  4. Nam Soo Kim (47 papers)
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets