Phoenixcodec: Taming Neural Speech Coding For Extreme Low-resource Scenarios

Abstract

This paper presents PhoenixCodec, a comprehensive neural speech coding and decoding framework designed for extremely low-resource conditions. The proposed system integrates an optimized asymmetric frequency-time architecture, a Cyclical Calibration and Refinement (CCR) training strategy, and a noise-invariant fine-tuning procedure. Under stringent constraints - computation below 700 MFLOPs, latency less than 30 ms, and dual-rate support at 1 kbps and 6 kbps - existing methods face a trade-off between efficiency and quality. PhoenixCodec addresses these challenges by alleviating the resource scattering of conventional decoders, employing CCR to enhance optimization stability, and enhancing robustness through noisy-sample fine-tuning. In the LRAC 2025 Challenge Track 1, the proposed system ranked third overall and demonstrated the best performance at 1 kbps in both real-world noise and reverberation and intelligibility in clean tests, confirming its effectiveness.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywan2025phoenixcodec

Related papers

• Pscodec: A Series Of High-fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders (2024)0.00
• Flexicodec: A Dynamic Neural Audio Codec For Low Frame Rates (2025)3.38
• Freecodec: A Disentangled Neural Speech Codec With Fewer Tokens (2024)4.52
• Optimizing Neural Speech Codec For Low-bitrate Compression Via Multi-scale Encoding (2024)0.00
• CQNV: A Combination Of Coarsely Quantized Bitstream And Neural Vocoder For Low Rate Speech Coding (2023)6.34
• Neural Feature Predictor And Discriminative Residual Coding For Low-bitrate Speech Coding (2022)6.77
• Msr-codec: A Low-bitrate Multi-stream Residual Codec For High-fidelity Speech Generation With Information Disentanglement (2025)2.35
• Mdctcodec: A Lightweight Mdct-based Neural Audio Codec Towards High Sampling Rate And Low Bitrate Scenarios (2024)8.09