# Factorized RVQ-GAN For Disentangled Speech Tokenization

arXiv: https://arxiv.org/abs/2506.15456 · HTML: https://mlsanity.com/paper/2506.15456/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Builds on (most cited first, 18 of 18)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Direct speech-to-speech translation with discrete units](https://mlsanity.com/paper/2107.05604/) (2021)
- [mHuBERT-147: A Compact Multilingual HuBERT Model](https://mlsanity.com/paper/2406.06371/) (2024)
- [The Zero Resource Speech Challenge 2021: Spoken language modelling](https://mlsanity.com/paper/2104.14700/) (2021)
- [Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech](https://mlsanity.com/paper/1911.09602/) (2019)
- [Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study](https://mlsanity.com/paper/2309.15800/) (2023)
- [SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation](https://mlsanity.com/paper/2205.08180/) (2022)
- [ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech](https://mlsanity.com/paper/2409.15897/) (2024)

## Built on by (most cited first, 1 of 1)

- [DSpAST: Disentangled Representations for Spatial Audio Reasoning with Large Language Models](https://mlsanity.com/paper/2509.13927/) (2025)

## Abstract (arXiv)

We propose Hierarchical Audio Codec (HAC), a unified neural speech codec that factorizes its bottleneck into three linguistic levels-acoustic, phonetic, and lexical-within a single model. HAC leverages two knowledge distillation objectives: one from a pre-trained speech encoder (HuBERT) for phoneme-level structure, and another from a text-based encoder (LaBSE) for lexical cues. Experiments on English and multilingual data show that HAC's factorized bottleneck yields disentangled token sets: one aligns with phonemes, while another captures word-level semantics. Quantitative evaluations confirm that HAC tokens preserve naturalness and provide interpretable linguistic information, outperforming single-level baselines in both disentanglement and reconstruction quality. These findings underscore HAC's potential as a unified discrete speech representation, bridging acoustic detail and lexical meaning for downstream speech generation and understanding tasks.