Using the Mimi codec for metalinguistic representations
Not on the map. Why?
Abstract (arXiv)
In this paper, we focus on the dictionary of 2048 tokens used in Mimi semantic token codebook, the neural codec of the Moshi language model. We show that the ABX experiment carried out with Mimi fails to capture the mapping of the semantic tokens to phone realisations. By realigning Mimi representations to the TIMIT corpus transcriptions, we show that the 2048 tokens IDs of the semantic codebook map to quadphone, triphone, biphone, phone and subphone realisations.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 9 of its 31 references that are in the map. First posted on arXiv 16 Aug 2026.
Builds on
9 of 31 references.
References · 9
- 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,313
- 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,625
- 2024Moshi: a speech-text foundation model for real-time dialoguecited by 550
- 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 456
- 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 393
- 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 388
- 2025Bringing Interpretability to Neural Audio Codecscited by 5
- 2023A Theory of Unsupervised Speech Recognitioncited by 4
- 2025On the Relation Between Speech Quality and Quantized Latent Representations of Neural Codecscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.