"text-to-sound generation" Papers
2 papers found
Conference
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
Zhen Ye, Peiwen Sun, Jiahe Lei et al.
AAAI 2025paperarXiv:2408.17175
75
citations
SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation
Koichi Saito, Dongjun Kim, Takashi Shibuya et al.
ICLR 2025arXiv:2405.18503
10
citations