# Exploring Token-Space Manipulation in Latent Audio Tokenizers

arXiv: https://arxiv.org/abs/2605.11192 · HTML: https://mlsanity.com/paper/2605.11192/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 42 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 30 of 35)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [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)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [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)
- [An Image is Worth 32 Tokens for Reconstruction and Generation](https://mlsanity.com/paper/2406.07550/) (2024)
- [AudioGen: Textually Guided Audio Generation](https://mlsanity.com/paper/2209.15352/) (2022)
- [Focal Modulation Networks](https://mlsanity.com/paper/2203.11926/) (2022)
- [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (2019)
- [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](https://mlsanity.com/paper/2005.11262/) (2020)
- [WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling](https://mlsanity.com/paper/2408.16532/) (2024)
- [Spirit LM: Interleaved Spoken and Written Language Model](https://mlsanity.com/paper/2402.05755/) (2024)
- [Image and Video Tokenization with Binary Spherical Quantization](https://mlsanity.com/paper/2406.07548/) (2024)
- [SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models](https://mlsanity.com/paper/2308.16692/) (2023)
- [Scaling Transformers for Low-Bitrate High-Quality Speech Coding](https://mlsanity.com/paper/2411.19842/) (2024)
- [BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec](https://mlsanity.com/paper/2409.05377/) (2024)
- [SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound](https://mlsanity.com/paper/2405.00233/) (2024)
- [Discrete Audio Tokens: More Than a Survey!](https://mlsanity.com/paper/2506.10274/) (2025)
- [Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling](https://mlsanity.com/paper/2509.08753/) (2025)
- [FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks](https://mlsanity.com/paper/2502.04465/) (2025)
- [Highly Compressed Tokenizer Can Generate Without Training](https://mlsanity.com/paper/2506.08257/) (2025)

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

- [ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding](https://mlsanity.com/paper/2609.11642/) (2026)

## Abstract (arXiv)

Neural audio codecs provide compact discrete representations for speech generation and manipulation. However, most codecs organize tokens as frame-level sequences, making it difficult to study or intervene on global factors of variation. In this work, we propose the Latent Audio Tokenizer for Token-space Editing (LATTE) that appends a fixed set of learnable latent tokens to the audio feature sequence and retains only these tokens for quantization and decoding. This design produces a compact, non-temporally aligned bottleneck in which each token can aggregate global information across the full utterance. We show that the resulting tokenizer preserves competitive reconstruction quality in low-bitrate speech coding settings while enabling simple token-space interventions. In particular, we find that swapping selected latent token positions between utterances can modify global attributes, such as speaker identity and background noise, and we evaluate these interventions on voice conversion and denoising tasks. Our results suggest that compact latent audio tokenizers can support controllable audio manipulation without supervision in task-specific editing models.