Neural audio coder reconstructs high quality sound at low bitrates
HE-NAC: High-Efficiency Neural Audio Coding via Hierarchical and Residual Multi-Band Quantization
Sound
Summary
Encoding audio into small digital files often loses important high-frequency sounds, making music less clear. The authors developed a new neural audio coder that splits sounds into different frequency bands and fixes missing details with smart learning techniques. This method keeps important low-frequency sounds while better preserving the overall quality of the music. Tests show it works better than some common audio compression standards at similar or lower file sizes.
What this means in practice
- •For audio codec developers: Integrate multi-band residual quantization techniques to improve audio compression efficiency and sound fidelity in neural audio codecs.
- •For streaming service engineers: Deliver higher quality music streams at equal or lower bitrates by implementing the HE-NAC encoding approach.$Commercial implications: Offers a product improvement by enhancing perceptual audio quality during streaming, which can attract more subscribers and reduce bandwidth costs.
Authors
Darius Pétermann, Wootaek Lim, Seungkwon Beack, Minje Kim
Abstract
High-fidelity audio coding requires faithful reconstruction of perceptually important high-frequency components, which are often lost due to the aggressive temporal decimation and quantization of neural codecs. State-of-the-art neural audio coding methods rely on adversarial learning to hallucinate these missing components, yielding perceptually plausible but imprecise reconstructions; a limitation for high-fidelity music applications. As a remedy, we propose high-efficiency neural audio coding (HE-NAC), which provides a multi-band extension of the popular residual vector quantization (RVQ) scheme. HE-NAC introduces an effective training mechanism that harmonizes a bitrate-free blind upsampling process, residual learning to compensate it with minimal bitrate, and a multi-head decoder architecture for band-specific reconstruction. As a result, HE-NAC achieves a balanced trade-off, reliably reconstructing the core-band ($\leq$ 3 kHz) component while preserving overall sound fidelity. Subjective listening tests and objective evaluations demonstrate that HE-NAC outperforms both the DAC baseline and MPEG HE-AAC at equal or lower bitrates.