# HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement

arXiv: https://arxiv.org/abs/2506.00843 · HTML: https://mlsanity.com/paper/2506.00843/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2025.

## Built on by (most cited first, 4 of 4)

- [Kanade: A Simple Disentangled Tokenizer for Spoken Language Modeling](https://mlsanity.com/paper/2602.00594/) (2026)
- [Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM](https://mlsanity.com/paper/2605.05927/) (2026)
- [STACodec: Semantic Token Assignment for Balancing Acoustic Fidelity and Semantic Information in Audio Codecs](https://mlsanity.com/paper/2602.06180/) (2026)
- [All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation](https://mlsanity.com/paper/2609.30416/) (2026)

## Abstract (arXiv)

Effective speech representations for spoken language models must balance semantic relevance with acoustic fidelity for high-quality reconstruction. However, existing approaches struggle to achieve both simultaneously. To address this, we introduce Hierarchical Acoustic and Semantic Representation Disentanglement (HASRD, pronounced `hazard'), a framework that factorizes self-supervised learning representations into discrete semantic and acoustic tokens. HASRD assigns the semantic representation to the first codebook, while encoding acoustic residuals in subsequent codebooks. This preserves ASR performance while achieving high-quality reconstruction. Additionally, we enhance HASRD's encoder efficiency, improving ASR performance without compromising reconstruction quality. Compared to SpeechTokenizer, HASRD achieves a 44% relative WER improvement, superior reconstruction quality, and 2x lower bitrate, demonstrating its effectiveness in disentangling acoustic and semantic information.