# Language-Codec: Bridging Discrete Codec Representations and Speech Language Models

arXiv: https://arxiv.org/abs/2402.12208 · HTML: https://mlsanity.com/paper/2402.12208/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2024.

## Built on by (most cited first, 6 of 6)

- [WavChat: A Survey of Spoken Dialogue Models](https://mlsanity.com/paper/2411.13577/) (2024)
- [Multimodal Duplex Interaction Agent](https://mlsanity.com/paper/2609.08977/) (2026)
- [Speech Watermarking with Discrete Intermediate Representations](https://mlsanity.com/paper/2412.13917/) (2024)
- [TokenMapper: A Step Toward Interoperable Speech Token Translation](https://mlsanity.com/paper/2609.12563/) (2026)
- [Rethinking Length-Based Training: Batch Composition and Loss Normalization in Speech Token Language Models](https://mlsanity.com/paper/2609.25890/) (2026)
- [How Robust Are Neural Audio Codecs for African Speech? A Multi-Task Benchmark and the Limits of Perceptual Quality](https://mlsanity.com/paper/2610.00154/) (2026)

## Abstract (arXiv)

In recent years, large language models have achieved significant success in generative tasks related to speech, audio, music, and other signal domains. A crucial element of these models is the discrete acoustic codecs, which serve as an intermediate representation replacing the mel-spectrogram. However, there exist several gaps between discrete codecs and downstream speech language models. Specifically, 1) Due to the reconstruction paradigm of the Codec model and the structure of residual vector quantization, the initial channel of the codebooks contains excessive information, making it challenging to directly generate acoustic tokens from weakly supervised signals such as text in downstream tasks. 2) numerous codebooks increases the burden on downstream speech language models. Consequently, leveraging the characteristics of speech language models, we propose Language-Codec. In the Language-Codec, we introduce a Masked Channel Residual Vector Quantization (MCRVQ) mechanism along with improved fourier transform structures and attention blocks, refined discriminator design to address the aforementioned gaps. We compare our method with competing audio compression algorithms and observe significant outperformance across extensive evaluations. Furthermore, we also validate the efficiency of the Language-Codec on downstream speech language models. The source code and pre-trained models can be accessed at https://github.com/jishengpeng/languagecodec .