{"ID":2867250,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.19186","arxiv_id":"2509.19186","title":"Improving Test-Time Performance of RVQ-based Neural Codecs","abstract":"The residual vector quantization (RVQ) technique plays a central role in recent advances in neural audio codecs. These models effectively synthesize high-fidelity audio from a limited number of codes due to the hierarchical structure among quantization levels. In this paper, we propose an encoding algorithm to further enhance the synthesis quality of RVQ-based neural codecs at test-time. Firstly, we point out the suboptimal nature of quantized vectors generated by conventional methods. We demonstrate that quantization error can be mitigated by selecting a different set of codes. Subsequently, we present our encoding algorithm, designed to identify a set of discrete codes that achieve a lower quantization error. We then apply the proposed method to pre-trained models and evaluate its efficacy using diverse metrics. Our experimental findings validate that our method not only reduces quantization errors, but also improves synthesis quality.","short_abstract":"The residual vector quantization (RVQ) technique plays a central role in recent advances in neural audio codecs. These models effectively synthesize high-fidelity audio from a limited number of codes due to the hierarchical structure among quantization levels. In this paper, we propose an encoding algorithm to further...","url_abs":"https://arxiv.org/abs/2509.19186","url_pdf":"https://arxiv.org/pdf/2509.19186v1","authors":"[\"Hyeongju Kim\",\"Junhyeok Lee\",\"Jacob Morton\",\"Juheon Lee\",\"Jinhyeok Yang\"]","published":"2025-09-23T16:02:27Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.SD\"]","methods":"[]","has_code":false}