# Improving X-Codec-2.0 for Multi-Lingual Speech: 25 Hz Latent Rate and 24 kHz Sampling

arXiv: https://arxiv.org/abs/2601.20185 · HTML: https://mlsanity.com/paper/2601.20185/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 13 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 12 of 12)

- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [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)
- [WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling](https://mlsanity.com/paper/2408.16532/) (2024)
- [SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models](https://mlsanity.com/paper/2308.16692/) (2023)
- [The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech](https://mlsanity.com/paper/2409.09305/) (2024)
- [Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model](https://mlsanity.com/paper/2408.17175/) (2024)
- [SNAC: Multi-Scale Neural Audio Codec](https://mlsanity.com/paper/2410.14411/) (2024)
- [UniCodec: Unified Audio Codec with Single Domain-Adaptive Codebook](https://mlsanity.com/paper/2502.20067/) (2025)
- [LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Models](https://mlsanity.com/paper/2510.15227/) (2025)
- [UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information](https://mlsanity.com/paper/2505.17426/) (2025)
- [Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-rates](https://mlsanity.com/paper/2509.09550/) (2025)

## Abstract (arXiv)

X-Codec-2.0 has shown strong performance in neural audio compression and multilingual speech modeling, operating at a 50 Hz latent rate and a 16 kHz sampling rate using frozen HuBERT features. While effective, this configuration limits temporal efficiency and audio fidelity. In this work, we explore a simple and effective modification by introducing additional pooling and increasing the decoder hop size. This reduces the latent rate from 50 Hz to 25 Hz and simultaneously raises the output sampling rate from 16 kHz to 24 kHz, improving efficiency and perceptual quality without altering the core architecture. Evaluated on the multilingual Common Voice 17 test set, the proposed configuration achieves a 0.29 MOS improvement over the original X-Codec-2.0 baseline based on UTMOSv2, and attains the best reported performance among all codecs operating at 25 Hz. The source code, checkpoints, and generation comparisons are released at hrefhttps://huggingface.co/Scicom-intl/xcodec2-25TPS-24khttps://huggingface.co/Scicom-intl/xcodec2-25TPS-24k.