# ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling

arXiv: https://arxiv.org/abs/2504.10344 · HTML: https://mlsanity.com/paper/2504.10344/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2025.

## Built on by (most cited first, 12 of 12)

- [MOSS-TTS Technical Report](https://mlsanity.com/paper/2603.18090/) (2026)
- [Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs](https://mlsanity.com/paper/2508.17863/) (2025)
- [Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization](https://mlsanity.com/paper/2601.23174/) (2026)
- [SAME: A Semantically-Aligned Music Autoencoder](https://mlsanity.com/paper/2605.18613/) (2026)
- [Scaling Speech Tokenizers with Diffusion Autoencoders](https://mlsanity.com/paper/2602.06602/) (2026)
- [Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction](https://mlsanity.com/paper/2506.09792/) (2025)
- [LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization](https://mlsanity.com/paper/2506.16738/) (2025)
- [U-Codec: Ultra Low Frame-rate Neural Speech Codec for Fast High-fidelity Speech Generation](https://mlsanity.com/paper/2510.16718/) (2025)
- [Exploring Token-Space Manipulation in Latent Audio Tokenizers](https://mlsanity.com/paper/2605.11192/) (2026)
- [AudioCodecBench: A Comprehensive Benchmark for Audio Codec Evaluation](https://mlsanity.com/paper/2509.02349/) (2025)
- [Recovering Performance in Speech Emotion Recognition from Discrete Tokens via Multi-Layer Fusion and Paralinguistic Feature Integration](https://mlsanity.com/paper/2601.17085/) (2026)
- [SAIL: Spatial Audio Intelligence with Large Language Models via Disentangled Acoustic-Spatial Encoding and Dual-Stream Q-Former](https://mlsanity.com/paper/2609.34347/) (2026)

## Abstract (arXiv)

Recent advancements in audio language models have underscored the pivotal role of audio tokenization, which converts audio signals into discrete tokens, thereby facilitating the application of language model architectures to the audio domain. In this study, we introduce ALMTokenizer, a novel low-bitrate and semantically rich audio codec tokenizer for audio language models. Prior methods, such as Encodec, typically encode individual audio frames into discrete tokens without considering the use of context information across frames. Unlike these methods, we introduce a novel query-based compression strategy to capture holistic information with a set of learnable query tokens by explicitly modeling the context information across frames. This design not only enables the codec model to capture more semantic information but also encodes the audio signal with fewer token sequences. Additionally, to enhance the semantic information in audio codec models, we introduce the following: (1) A masked autoencoder (MAE) loss, (2) Vector quantization based on semantic priors, and (3) An autoregressive (AR) prediction loss. As a result, ALMTokenizer achieves competitive reconstruction performance relative to state-of-the-art approaches while operating at a lower bitrate. Within the same audio language model framework, ALMTokenizer outperforms previous tokenizers in audio understanding and generation tasks.