Tencent Music Tianqin Lab's Applications and Practices of Audio Quality AIGC
The article details Tencent Music's Tianqin Lab research on audio quality AIGC, covering background upgrades, music separation techniques, real‑time super‑resolution, the industry‑first premium master‑track technology, and a Q&A on vocal separation, illustrating practical AI-driven audio enhancements.
This article presents the work of Tencent Music's Tianqin Lab on audio quality AIGC, covering background, music separation, music super‑resolution, and the industry‑first “Premium Master Track” technology.
Background: QQ Music upgraded its audio quality system in version 12.0, introducing SQ, HQ, and Premium 2.0, and becoming the first Chinese streaming service to adopt Dolby Atmos.
Music Separation: The lab reviews the evolution from early Conv‑TasNet and Spleeter to recent BSRNN models that split audio into sub‑bands, model temporal and frequency sequences, and enable applications such as premium spatial audio, K‑song accompaniment, low‑frequency assistance for the hearing‑impaired, and AI‑generated content detection.
Music Super‑Resolution: Described as a real‑time on‑device enhancement that converts CD/MP3 sources to Hi‑Res 96 kHz/24‑bit quality for the Premium 2.0 listening experience.
Premium Master Track: Explains the concept of a master track (192 kHz/24‑bit), the need for low‑frequency repair and high‑frequency restoration, and how the new model reduces inference cost while improving objective and subjective metrics, leading to increased usage statistics.
Finally, a brief Q&A addresses vocal‑track separation capabilities, confirming that QQ Music can isolate both choir and harmony vocals.
DataFunSummit
Official account of the DataFun community, dedicated to sharing big data and AI industry summit news and speaker talks, with regular downloadable resource packs.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.