ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation

19 Sep 2023  ·  Yatong Bai, Trung Dang, Dung Tran, Kazuhito Koishida, Somayeh Sojoudi ·

Diffusion models are instrumental in text-to-audio (TTA) generation. Unfortunately, they suffer from slow inference due to an excessive number of queries to the underlying denoising network per generation. To address this bottleneck, we introduce ConsistencyTTA, a framework requiring only a single non-autoregressive network query, thereby accelerating TTA by hundreds of times. We achieve so by proposing "CFG-aware latent consistency model," which adapts consistency generation into a latent space and incorporates classifier-free guidance (CFG) into model training. Moreover, unlike diffusion models, ConsistencyTTA can be finetuned closed-loop with audio-space text-aware metrics, such as CLAP score, to further enhance the generations. Our objective and subjective evaluation on the AudioCaps dataset shows that compared to diffusion-based counterparts, ConsistencyTTA reduces inference computation by 400x while retaining generation quality and diversity.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Audio Generation AudioCaps Consistency TTA (Single-step generation) FAD 2.18 # 11
FD 20.44 # 6