14 January 2026 in IEEE Transactions on Affective Computing
Current emotional text-to-speech tasks have achieved high-quality emotional speech by incorporating emotion modules into text-to-speech models. However, there has been limited in-depth research on embedding emotion modules within TTS models, and the expression of emotion in synthesized speech is constrained by both the TTS model and the emotion module, often preventing optimal results. This paper presents a novel TTS model, Grad-DiT, based on the DiT architecture of diffusion models, aimed at enhancing the naturalness and expressiveness of TTS. Unlike traditional U-net architectures, Grad-DiT leverages the Transformer architecture to better capture contextual information in text, resulting in more natural speech generation. Building on this model, we propose Emo-DiT, which incorporates an Emotion Feature Reconstruction (EFR) module to enable the synthesis of speech with specific emotional expressions. Experimental results show that Grad-DiT not only surpasses existing TTS models in speech quality but also significantly improves real-time performance and inference speed. Compared to traditional emotion generation methods, Emo-DiT offers more precise emotional expression, enabling the synthesis of speech with distinctive emotional characteristics and providing substantial support for future applications in emotional speech synthesis.
21 February 2026 in International Journal of Pattern Recognition and Artificial Intelligence
2 March 2026 in SSRN Electronic Journal
Zero- and few-shot recognition is bottlenecked by the modality gap---a systematic misalignment where textual anchors fail to match the visual manifold. We present VASMA, a Manifold-Guided Geometric Information Fusion framework bridging this topological void by enforcing strict geometric consistency across heterogeneous evidence sources.Transcending mere data expansion, VASMA utilizes LLM-expanded prompts as shared semantic anchors to orchestrate dual-domain evidence accumulation. It synergizes Pixel-Level coverage with Latent Manifold fidelity, ensuring comprehensive decision space exploration. Crucially, a tangent-space projection mechanism acts as a geometric filter, strictly aligning synthetic features with the intrinsic visual distribution. Heterogeneous streams are integrated into a Unified Cache, enabling auditable and calibrated fusion via a shared query kernel.VASMA establishes state-of-the-art results across 11 datasets, surpassing zero-shot CLIP by +24.6\% while achieving 73.9\% few-shot accuracy (+15.0 point gain). These findings substantiate that correcting the anchor-real geometric mismatch is prerequisite for robust multi-source fusion in data-scarce regimes.