SDAIMar 2

CodecFlow: Efficient Bandwidth Extension via Conditional Flow Matching in Neural Codec Latent Space

arXiv:2603.02022v21 citationsh-index: 3
AI Analysis

This addresses the problem of improving speech clarity and intelligibility for audio applications, with incremental improvements in efficiency and fidelity.

The paper tackles speech bandwidth extension by restoring high-frequency content from low-bandwidth speech, achieving strong spectral fidelity and enhanced perceptual quality on tasks like 8 kHz to 16 kHz and 44.1 kHz conversion.

Speech Bandwidth Extension improves clarity and intelligibility by restoring/inferring appropriate high-frequency content for low-bandwidth speech. Existing methods often rely on spectrogram or waveform modeling, which can incur higher computational cost and have limited high-frequency fidelity. Neural audio codecs offer compact latent representations that better preserve acoustic detail, yet accurately recovering high-resolution latent information remains challenging due to representation mismatch. We present CodecFlow, a neural codec-based BWE framework that performs efficient speech reconstruction in a compact latent space. CodecFlow employs a voicing-aware conditional flow converter on continuous codec embeddings and a structure-constrained residual vector quantizer to improve latent alignment stability. Optimized end-to-end, CodecFlow achieves strong spectral fidelity and enhanced perceptual quality on 8 kHz to 16 kHz and 44.1 kHz speech BWE tasks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes