TQCodec: Towards neural audio codec for high-fidelity music streaming

TL;DR

Evaluations on diverse music datasets demonstrate that TQCodec achieves superior audio quality at target bitrates, making it well-suited for high-quality audio applications.

Abstract

We propose TQCodec, a neural audio codec designed for high-bitrate, high-fidelity music streaming. Unlike existing neural codecs that primarily target ultra-low bitrates (<= 16kbps), TQCodec operates at 44.1 kHz and supports bitrates from 32 kbps to 128 kbps, aligning with the standard quality of modern music streaming platforms. The model adopts an encoder-decoder architecture based on SEANet for efficient on-device computation and introduces several enhancements: an imbalanced network design for improved quality with low overhead, SimVQ for mid-frequency detail preservation, and a phase-aware waveform loss. Additionally, we introduce a perception-driven band-wise bit allocation strategy to prioritize perceptually critical lower frequencies. Evaluations on diverse music datasets demonstrate that TQCodec achieves superior audio quality at target bitrates, making it well-suited for high-quality audio applications.

Figures (2)

• Figure 1: Illustration of our subband modeling.
• Figure 2: Spectrogram visualization, where the RVQ fails to reconstruct the mid-frequency clearly (above 4000Hz).