ABSTRACT The emotional recognition of coal mine workers across dialects faces significant challenges due to the acoustic differences between dialects. Traditional methods fail to distinguish between dialect‐specific and emotional features, leading to poor generalization. To address this, this paper proposes a recognition framework based on speech feature disentanglement, which improves the model's robustness by decoupling shared emotional features from dialect‐specific features. Specifically, the speech signal is transformed into high‐resolution time‐frequency feature maps, and a Siamese Neural Network (SNN) is used for feature disentanglement, separating emotional features into shared public feature maps across dialects and dialect/speaker‐specific private feature maps. The public encoder maximizes mutual information between same‐class samples to learn dialect‐independent common emotional representations, while the private encoder extracts dialect‐related personalized features, reducing the interference of language differences in emotion recognition. Additionally, dialect corpus information is incorporated into the task. Experimental results show that this method significantly improves emotional recognition accuracy in coal mine multilingual environments, while enhancing the system's environmental adaptability.

E-commerce business is revolutionizing our shopping experiences by providing convenient and straightforward services. One of the most fundamental problems is how to balance the demand and supply in market segments to build an efficient platform. While conventional machine learning models have achieved great success on data-sufficient segments, it may fail in a large-portion of segments in E-commerce platforms, where there are not sufficient records to learn well-trained models. In this paper, we tackle this problem in the context of market segment demand prediction. The goal is to facilitate the learning process in the target segments by leveraging the learned knowledge from data-sufficient source segments. Specifically, we propose a novel algorithm, RMLDP, to incorporate a multi-pattern fusion network (MPFN) with a meta-learning paradigm. The multi-pattern fusion network considers both local and seasonal temporal patterns for segment demand prediction. In the meta-learning paradigm, transferable knowledge is regarded as the model parameter initialization of MPFN, which are learned from diverse source segments. Furthermore, we capture the segment relations by combining data-driven segment representation and segment knowledge graph representation and tailor the segment-specific relations to customize transferable model parameter initialization. Thus, even with limited data, the target segment can quickly find the most relevant transferred knowledge and adapt to the optimal parameters. We conduct extensive experiments on two large-scale industrial datasets. The results justify that our RMLDP outperforms a set of state-of-the-art baselines. Besides, RMLDP has been deployed in Taobao, a real-world E-commerce platform. The online A/B testing results further demonstrate the practicality of RMLDP.