Zero-shot text-to-speech (TTS) can reproduce an unseen speaker from a short reference recording, but typically entangles speaker identity and accent within the same reference. We introduce DEFINE, an end-to-end framework that decouples these factors by conditioning speaker identity and target accent on separate audio e...
Ambuj Mehrish, Abhinaba Roy, Alex Ivanov et al.· 0 citations
This work introduces Hypergraph-Regularized Gramian Volumes (HyVol), a training-time module that incorporates semantic relations prior to evaluating the original volume loss of Gram, and removes the hypergraph after training, leaving the backbone-only architecture, original scoring function, and retrieval cost unchange...
Treating the roll-out group as a graph rather than a ballot box turns a brittle vote into a calibrated, graded, self-supervised reward at no extra roll-out cost.
This paper introduces SonicMaster, the first unified generative model for music restoration and mastering that addresses a broad spectrum of audio artifacts with text-based control and significantly improves sound quality across all artifact categories.
J. Melechovský, Ambuj Mehrish, Dorien Herremans· arXiv.org· 11 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
