Search papers, labs, and topics across Lattice.
Affiliation:
2
0
2
Emotion vectors are not monolithic directions: decoupling the generic shift away from neutrality from the emotion-specific residual more than doubles training-free steering precision in frozen TTS backbones.
SongCraft, a latent flow matching based model trained for both generation and fine-grained editing, is presented, showing that a single model can support editing of lyrics, vocal melody, beats, and singer identity and the trade-off between reconstruction quality and editability is studied.