.png){kind=icon}
.png){kind=icon}
Return
Efficient Parallel Audio Generation Using Group Masked Language Modeling
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2024.3381910.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We present a fast and high-quality codec language model for parallel audio generation. While SoundStorm, a state-of-the-art parallel audio generation model, accelerates inference speed compared to autoregressive models, it still suffers from slow inference due to iterative sampling. To resolve this problem, we propose Group-Masked Language Modeling (G-MLM) and Group Iterative Parallel Decoding (G-IPD) for efficient parallel audio generation. Both the training and sampling schemes enable the model to synthesize high-quality audio with a small number of iterations by effectively modeling the group-wise conditional dependencies. In addition, our model employs a cross-attention-based architecture to capture the speaker style of the prompt voice and improves computational efficiency. Experimental results demonstrate that our proposed model outperforms the baselines in prompt-based audio generation.
Keywords:
Parallel audio generation
neural audio codec
Journal
IF:
9.6
Papers:
1.1W
Citations:
1.7W