An Empirical Analysis of Discrete Unit Representations in Speech Language Modeling Pre-training

Yanis Labrak, Richard Dufour, Mickaël Rouvier. An Empirical Analysis of Discrete Unit Representations in Speech Language Modeling Pre-training. In Kamil Ekstein, Miloslav Konopík, Ondrej Prazák, Frantisek Pártl, editors, Text, Speech, and Dialogue - 28th International Conference, TSD 2025, Erlangen, Germany, August 25-28, 2025, Proceedings, Part I. Volume 16029 of Lecture Notes in Computer Science, pages 13-24, Springer, 2025. [doi]

@inproceedings{LabrakDR25,
  title = {An Empirical Analysis of Discrete Unit Representations in Speech Language Modeling Pre-training},
  author = {Yanis Labrak and Richard Dufour and Mickaël Rouvier},
  year = {2025},
  doi = {10.1007/978-3-032-02548-7_2},
  url = {https://doi.org/10.1007/978-3-032-02548-7_2},
  researchr = {https://researchr.org/publication/LabrakDR25},
  cites = {0},
  citedby = {0},
  pages = {13-24},
  booktitle = {Text, Speech, and Dialogue - 28th International Conference, TSD 2025, Erlangen, Germany, August 25-28, 2025, Proceedings, Part I},
  editor = {Kamil Ekstein and Miloslav Konopík and Ondrej Prazák and Frantisek Pártl},
  volume = {16029},
  series = {Lecture Notes in Computer Science},
  publisher = {Springer},
  isbn = {978-3-032-02548-7},
}