Improving X-Codec-2.0 for Multi-Lingual Speech: 25 Hz Latent Rate and 24 kHz Sampling
Not on the map. Why?
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.
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
12 of 13 references.
References · 12
- 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
- 2024Moshi: a speech-text foundation model for real-time dialoguecited by 568
- 2023High-Fidelity Audio Compression with Improved RVQGANcited by 431
- 2024WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modelingcited by 129
- 2023SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Modelscited by 87
- 2024The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speechcited by 83
- 2024Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Modelcited by 72
- 2024SNAC: Multi-Scale Neural Audio Codeccited by 43
- 2025UniCodec: Unified Audio Codec with Single Domain-Adaptive Codebookcited by 10
- 2025LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Modelscited by 3
- 2025UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic informationcited by 2
- 2025Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-ratescited by 2
Built on by
Not cited yet.