ensemble
发表于 2025-4-1 03:35:42
http://reply.papertrans.cn/67/6697/669627/669627_61.png
falsehood
发表于 2025-4-1 06:55:06
SACL: Sequential Augmentation with Curriculum Learning in Dataset Level and resources. To validate our method, we conduct experiments on the MET-MEME dataset for a multimodal emotion classification task and deeply analyze the impact of curriculum learning on the training results. The results prove the effectiveness of our method.
芳香一点
发表于 2025-4-1 11:39:04
Classifiers Guided Controllable Text Generation for Discrete Diffusion Language Modelsained controllable tasks demonstrate the effectiveness of the proposed algorithms, achieving success rates up to 99% on certain tasks. Furthermore, the inherent multi-modality problem in discrete diffusion models is mitigated by framing multi-modality suppression as a controllable generation task. T
atrophy
发表于 2025-4-1 15:03:05
AugMixSpeech: A Data Augmentation Method and Consistency Regularization for Mandarin Automatic Speec intrinsic features of the data. Extensive experiments on the validation and test of Aishell-1 achieve recognition accuracy of 4.23% and 4.79%, which outperforms existing approaches and demonstrates its effectiveness in automatic speech recognition.