Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers
This work addresses a critical bottleneck in audio synthesis for AI applications, offering a competitive LM-based alternative to diffusion models, though it is incremental in improving existing methods.
The paper tackled the performance gap between language model (LM) and diffusion-based methods in text-to-audio generation by identifying limitations in residual vector quantization (RVQ) and proposing Siren, a framework with multiple transformers and anti-causal alignment, which achieved state-of-the-art results.
While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based models by a non-trivial margin. We identify a critical dilemma underpinning this gap: incorporating more RVQ layers improves audio reconstruction fidelity but exceeds the generation capacity of conventional LMs. To address this, we first analyze RVQ dynamics and uncover two key limitations: 1) orthogonality of features across RVQ layers hinders effective LMs training, and 2) descending semantic richness in tokens from deeper RVQ layers exacerbates exposure bias during autoregressive decoding. Based on these insights, we propose Siren, a novel LM-based framework that employs multiple isolated transformers with causal conditioning and anti-causal alignment via reinforcement learning. Extensive experiments demonstrate that Siren outperforms both existing LM-based and diffusion-based T2A systems, achieving state-of-the-art results. By bridging the representational strengths of LMs with the fidelity demands of audio synthesis, our approach repositions LMs as competitive contenders against diffusion models in T2A tasks. Moreover, by aligning audio representations with linguistic structures, Siren facilitates a promising pathway toward unified multi-modal generation frameworks.