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

TL;DR

TQCodec is a neural audio codec designed for high-fidelity music streaming at standard quality bitrates, utilizing innovative architecture and perceptual strategies to outperform existing codecs in audio quality.

Contribution

It introduces a novel neural codec operating at 44.1 kHz for high-bitrate music streaming, with enhancements like SimVQ and phase-aware loss for improved quality.

Findings

Achieves superior audio quality at 32-128 kbps

Operates efficiently on-device with SEANet-based architecture

Outperforms existing neural codecs in listening tests

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.