# LoSATok: Low-Dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation

arXiv: https://arxiv.org/abs/2605.27840 · HTML: https://mlsanity.com/paper/2605.27840/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 48 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 26 of 26)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://mlsanity.com/paper/2303.17395/) (2023)
- [GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot](https://mlsanity.com/paper/2412.02612/) (2024)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [LP-MusicCaps: LLM-Based Pseudo Music Captioning](https://mlsanity.com/paper/2307.16372/) (2023)
- [SNAC: Multi-Scale Neural Audio Codec](https://mlsanity.com/paper/2410.14411/) (2024)
- [MiDashengLM: Efficient Audio Understanding with General Audio Captions](https://mlsanity.com/paper/2508.03983/) (2025)
- [EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer](https://mlsanity.com/paper/2409.10819/) (2024)
- [LeVo: High-Quality Song Generation with Multi-Preference Alignment](https://mlsanity.com/paper/2506.07520/) (2025)
- [XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs](https://mlsanity.com/paper/2506.23325/) (2025)
- [Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation](https://mlsanity.com/paper/2511.05516/) (2025)
- [Semantic-VAE: Semantic-Alignment Latent Representation for Better Speech Synthesis](https://mlsanity.com/paper/2509.22167/) (2025)
- [UALM: Unified Audio Language Model for Understanding, Generation and Reasoning](https://mlsanity.com/paper/2510.12000/) (2025)
- [X-ARES: A Comprehensive Framework for Assessing Audio Encoder Performance](https://mlsanity.com/paper/2505.16369/) (2025)
- [UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities](https://mlsanity.com/paper/2509.24391/) (2025)
- [SemanticVocoder: Bridging Audio Generation and Audio Understanding via Semantic Latents](https://mlsanity.com/paper/2602.23333/) (2026)
- [WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling](https://mlsanity.com/paper/2605.06407/) (2026)
- [UniSRCodec: Unified and Low-Bitrate Single Codebook Codec with Sub-Band Reconstruction](https://mlsanity.com/paper/2601.02776/) (2026)

## Abstract (arXiv)

Audio tokenizers are fundamental to unifying audio understanding and generation. Understanding requires high-level semantics, while generation demands semantic and acoustic details. Existing unified tokenizers jointly encode both in high-dimensional continuous latents, which increases the modeling burden of Diffusion Transformers (DiTs) for generation. We propose LoSATok, a low-dimensional audio tokenizer for cross-domain audio understanding and generation. Motivated by the observation that 1280-dimensional semantic encoder features are compressible, we introduce a Semantic Bottleneck that compresses them into 128 dimensions, regularized by the proposed time-relation loss for temporal feature consistency. We further design a dual-level semantic supervision method that leverages both high- and low-dimensional semantic signals, enabling the tokenizer to jointly capture semantics and acoustic details within a compact latent space. Experiments on speech, music, and general audio show that SemBo preserves strong low-dimensional semantic capacity and LoSATok retains competitive understanding performance compared with several semantic representations, while consistently improving DiT modeling performance on speech, music, and audio generation. These results demonstrate that LoSATok's low-dimensional representations can effectively support audio understanding and generation. Our code is provided at https://github.com/wxzyd123/LoSATok.