Ultra-Low-Bitrate Mel-Spectrogram-based Neural Speech Coding with Flow-Matching-based Refinement and Vocoding-driven Reconstruction
Hui-Peng Du, Xiao-Hang Jiang, Yuan Tian, Yang Ai, and Zhen-Hua Ling
Abstract
Ultra-low-bitrate speech coding is pivotal for bandwidth-constrained communication and deep compression,
yet maintaining naturalness and speaker identity at such extreme bit budgets remains challenging due to pronounced information loss and quantization instability.
To this end, we propose FMelCodec, an ultra-low-bitrate neural speech codec in the mel-spectrogram domain, cast as a three-stage coding–refinement–reconstruction
(CRR) framework that can operate at as low as 250 bps. In the CRR framework, the front-end mel-spectrogram coding stage employs a highly aggressive 640× compression/decompression
encoder–decoder structure with a single 1024-entry VQ codebook, coupled with an online clustering strategy that reassigns underused codewords to prevent codebook
collapse and preserve codebook diversity. The subsequent conditional flow matching (CFM)-based mel-spectrogram refinement stage leverages a lightweight velocity-field estimator and CFM-based solver
to refine the codec-degraded mel-spectrogram produced by the preceding decoder, and adopts a self-consistency training scheme that supports fewer iterative inference steps
for the purpose of reducing computational overhead.
Finally, the vocoding-driven waveform reconstruction stage employs a HiFi-GAN vocoder to faithfully reconstruct waveform from the refined mel-spectrogram.
Experiments conducted on two datasets spanning two sampling rates show that, under ultra-low-bitrate constraints of 250 bps for 16 kHz and 750 bps for 48 kHz, both
objective and subjective evaluations consistently demonstrate that FMelCodec achieves higher speech reconstruction quality and speaker similarity, while incurring lower computational and model complexity.
