Recent efforts on text-to-audio (TTA) generation are starting to explore fine-grained controllability, e.g., precise timing control, with innovations on conditioning techniques or training-free latent manipulations. However, constrained by data scarcity, their generation performance at scale is still limited. In this study, we recast high-controllability TTA generation as a multi-task learning problem, and introduce a progressive diffusion modeling approach, ControlAudio. Our method adeptly fits distributions conditioned on fine-grained information, including text, timing, and phoneme features, through a step-by-step strategy. First, we propose a data construction method spanning both annotation and simulation, augmenting condition information in the sequence of text, timing, and phoneme. Second, at the model training stage, we pretrain a scalable diffusion transformer (DiT) on large-scale text-audio pairs, achieving high-fidelity TTA generation, and then incrementally integrate the timing and phoneme features, expanding controllability. Finally, at the inference stage, we propose progressively guided generation, which sequentially emphasizes more fine-grained information, aligning inherently with the coarse-to-fine sampling nature of DiT. Extensive experiments show that ControlAudio achieves state-of-the-art performance in terms of temporal accuracy and speech clarity, significantly outperforming existing methods on both objective and subjective evaluations. Demo samples are available at: https://control-audio.github.io/Control-Audio.

Works on learning job title representation are mainly based on Job-Transition Graph, built from the working history of talents. However, since these records are usually messy, this graph is very sparse, which affects the quality of the learned representation and hinders further analysis. To address this specific issue, we propose to enrich the graph with additional nodes that improve the quality of job title representation. Specifically, we construct Job-Transition-Tag Graph, a heterogeneous graph containing two types of nodes, i.e., job titles and tags (i.e., words related to job responsibilities or functionalities). Along this line, we reformulate job title representation learning as the task of learning node embedding on the Job-Transition-Tag Graph. Experiments on two datasets show the interest of our approach.