Journal article · 2025 · Open access

Recent Advances in Discrete Speech Tokens: A Review

Yiwei Guo, Zhihan Li, Hankun Wang, Bohan Li, Chongtian Shao, Hanglei Zhang, Chenpeng Du, Xie Chen, Shujie Liu, Kai Yu

IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(4), 4184–4204 · Published 12 December 2025 · DOI 10.1109/tpami.2025.3643619

Open PDFView at the publisherCite this paper

In brief

“Recent Advances in Discrete Speech Tokens: A Review” is a 2025 journal article by Yiwei Guo and 9 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 95 citations as of 18 November 2026, which puts it in the top 1% of works published in 2025 by citations. It is open access under a public domain licence: the full text is free to read at arXiv (Cornell University).

Citations
95
Most cited in
2026 (62)
Field-weighted impact
14.68
References
280
Authors
10

Abstract

The rapid advancement of speech generation technologies in the era of large language models (LLMs) has established discrete speech tokens as a foundational paradigm for speech representation. These tokens, characterized by their discrete, compact, and concise nature, are not only advantageous for efficient transmission and storage, but also inherently compatible with the language modeling framework, enabling seamless integration of speech into text-dominated LLM architectures. Current research categorizes discrete speech tokens into two principal classes: acoustic tokens and semantic tokens, each of which has evolved into a rich research domain characterized by unique design philosophies and methodological approaches. This survey systematically synthesizes the existing taxonomy and recent innovations in discrete speech tokenization, conducts a critical examination of the strengths and limitations of each paradigm, and presents systematic experimental comparisons across token types. Furthermore, we identify persistent challenges in the field and propose potential research directions, aiming to offer actionable insights to inspire future advancements in the development and application of discrete speech tokens.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Guo, Y., Li, Z., Wang, H., Li, B., Shao, C., Zhang, H., Du, C., Chen, X., Liu, S., & Yu, K. (2025). Recent Advances in Discrete Speech Tokens: A Review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(4), 4184–4204. https://doi.org/10.1109/tpami.2025.3643619

MLA 9

Guo, Yiwei, et al. “Recent Advances in Discrete Speech Tokens: A Review.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 48, no. 4, 2025, pp. 4184–4204. https://doi.org/10.1109/tpami.2025.3643619.

Chicago

Guo, Yiwei, Zhihan Li, Hankun Wang, Bohan Li, Chongtian Shao, Hanglei Zhang, Chenpeng Du, Xie Chen, Shujie Liu, and Kai Yu. 2025. “Recent Advances in Discrete Speech Tokens: A Review.” IEEE Transactions on Pattern Analysis and Machine Intelligence 48 (4): 4184–4204. https://doi.org/10.1109/tpami.2025.3643619.

Harvard

Guo, Y. et al. (2025) ‘Recent Advances in Discrete Speech Tokens: A Review’, IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(4), pp. 4184–4204. doi:10.1109/tpami.2025.3643619.

IEEE

Y. Guo et al., “Recent Advances in Discrete Speech Tokens: A Review,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 48, no. 4, pp. 4184–4204, 2025, doi: 10.1109/tpami.2025.3643619.

BibTeX

@article{guo2025recent,
  title     = {{Recent Advances in Discrete Speech Tokens: A Review}},
  author    = {Guo, Yiwei and Li, Zhihan and Wang, Hankun and Li, Bohan and Shao, Chongtian and Zhang, Hanglei and Du, Chenpeng and Chen, Xie and Liu, Shujie and Yu, Kai},
  journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year      = {2025},
  volume    = {48},
  number    = {4},
  pages     = {4184--4204},
  doi       = {10.1109/tpami.2025.3643619},
  url       = {https://doi.org/10.1109/tpami.2025.3643619}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis

  • speech tokenization
  • semantic tokens
  • large language models
  • speech generation
  • speech representation

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Guo, Y., Li, Z., Wang, H., Li, B., Shao, C., Zhang, H., Du, C., Chen, X., Liu, S., & Yu, K. (2025). Recent Advances in Discrete Speech Tokens: A Review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(4), 4184–4204. https://doi.org/10.1109/tpami.2025.3643619

How many times has this paper been cited?

95 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Yiwei Guo, Zhihan Li, Hankun Wang, Bohan Li, Chongtian Shao, Hanglei Zhang, Chenpeng Du, Xie Chen, Shujie Liu, Kai Yu.

What is the DOI of this paper?

10.1109/tpami.2025.3643619, permanently at https://doi.org/10.1109/tpami.2025.3643619. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.