2024/06/25 by Marco Comunità, Zhi Zhong, Comunità, Marco +17 · 7 citations
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music Technology and Sound Studies #Music and Audio Processing #Sound (cs.SD) #Speech and Audio Processing #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2406.17672
openalex publication_date 2024/06/25 · openalex created_date 2024/06/28 · openalex updated_date 2026/07/28
Recent advances in generative models that iteratively synthesize audio clips sparked great success to text-to-audio synthesis (TTA), but with the cost of slow synthesis speed and heavy computation. Although there have been attempts to accelerate the iterative procedure, high-quality TTA systems remain inefficient due to hundreds of iterations required in the inference phase and large amount of model parameters. To address the challenges, we propose SpecMaskGIT, a light-weighted, efficient yet effective TTA model based on the masked generative modeling of spectrograms. First, SpecMaskGIT synthesizes a realistic 10s audio clip by less than 16 iterations, an order-of-magnitude less than previous iterative TTA methods. As a discrete model, SpecMaskGIT outperforms larger VQ-Diffusion and auto-regressive models in the TTA benchmark, while being real-time with only 4 CPU cores or even 30x faster with a GPU. Next, built upon a latent space of Mel-spectrogram, SpecMaskGIT has a wider range of applications (e.g., the zero-shot bandwidth extension) than similar methods built on the latent wave domain. Moreover, we interpret SpecMaskGIT as a generative extension to previous discriminative audio masked Transformers, and shed light on its audio representation learning potential. We hope our work inspires the exploration of masked audio modeling toward further diverse scenarios.