Search papers, labs, and topics across Lattice.
Dasheng AudioGen is introduced as a unified framework for generating coherent audio scenes from text, addressing the fragmentation of audio generation tasks. The model uses structured multi-view captions to decouple complex acoustic scenes and employs a high-dimensional unified semantic-acoustic representation as a shared latent space. Experiments show that Dasheng AudioGen achieves performance approaching real-world recordings in mixed-audio categories and remains competitive with specialized models in single-type generation tasks.
Finally, a single model generates realistic and coherent audio scenes from text, rivaling specialized models and even approaching real-world recordings.
Audio generation has long been fragmented, with speech, music, and sound effects produced by domain-specific models that fail to jointly generate coherent audio scenes from a single description. The key obstacles are insufficient fine-grained supervision for real-world mixed audio and limited acoustic representations for modeling concurrent audio components. We present Dasheng AudioGen, a unified framework for generating general mixed-audio scenes from text. Dasheng AudioGen introduces structured multi-view captions, which explicitly decouple complex acoustic scenes into complementary description views, thereby enabling fine-grained control over audio layers. Furthermore, we employ a high-dimensional unified semantic-acoustic representation as the shared latent space. It injects semantic priors that facilitate cross-modal training convergence, while its high-dimensional feature space provides sufficient capacity to disentangle and fuse concurrent audio components effectively. With these designs, a simple flow-matching DiT achieves high-quality end-to-end audio scene generation. We also establish a comprehensive evaluation pipeline for audio scene generation. Experiments demonstrate that Dasheng AudioGen achieves performance approaching real-world recordings in mixed-audio categories, while remaining competitive with specialized models in single-type generation tasks. Demos are available at https://nieeim.github.io/Dasheng-AudioGen-Web/.
