Accurate emotion recognition from speech is important for applications like smart health care, smart entertainment, and other smart services. High accuracy emotion recognition from Chinese speech is challenging due to the complexities of the Chinese language. In this paper, we explore how to improve the accuracy of speech emotion recognition, including speech signal feature extraction and emotion classification methods. Five types of features are extracted from a speech sample: mel frequency cepstrum coefficient (MFCC), pitch, formant, short-term zero-crossing rate and short-term energy. By comparing statistical features with deep features extracted by a Deep Belief Network (DBN), we attempt to find the best features to identify the emotion status for speech. We propose a novel classification method that combines DBN and SVM (support vector machine) instead of using only one of them. In addition, a conjugate gradient method is applied to train DBN in order to speed up the training process. Gender-dependent experiments are conducted using an emotional speech database created by the Chinese Academy of Sciences. The results show that DBN features can reflect emotion status better than artificial features, and our new classification approach achieves an accuracy of 95.8%, which is higher than using either DBN or SVM separately. Results also show that DBN can work very well for small training databases if it is properly designed.

Federated learning enables cooperative computation between multiple participants while protecting user privacy. Currently, federated learning algorithms assume that all participants are trustworthy and their systems are secure. However, the following problems arise in real-world scenarios: (1) Malicious clients disrupt federated learning through model poisoning and data poisoning attacks. Although some research has proposed secure aggregation methods to solve this problem, most methods have limitations. (2) Due to the variance in data quality and computational resources among participants, rewards cannot be distributed equally. Some clients also exhibit free-rider behavior, seeking to cheat the reward system and manipulate global models. Evaluating client contribution and distributing rewards also present challenges. To address these challenges, we design a trustworthy federated framework to ensure secure computing throughout the federated task process. First, we propose a malicious model detection method for secure model aggregation. Then, we also propose a fair method of assessing contribution to identify client-side free-riding behavior. Lastly, we develop a computation process grounded in blockchain and smart contracts to guarantee the trustworthiness and fairness of federated tasks. To validate the performance of our framework, we simulate different types of client attacks and contribution evaluation scenarios on several open-source datasets. The experiments show that our framework guarantees the federated task’s credibility and achieves fair client contribution evaluation.

Federated learning enables multiple clients to learn a general model without sharing local data, and the federated learning system also improves information security and advances responsible artificial intelligence (AI). However, the data of different clients in the system are non-independently and identically distributed (IID), which results in weight divergence, especially for complex graph data extraction. This article proposes a novel feature-contrastive graph federated (FcgFed) learning approach to improve the robustness of the federated learning system in graph data. First, we design an architecture for FcgFed learning systems to analyze graph information. Furthermore, we present a graph federated learning method based on contrastive learning to alleviate the weight divergence in federated learning. The experiments in node classification and graph classification demonstrate that our method achieves better performance than model-contrastive federated learning (MOON) and federated average (FedAvg). We also test the adaptability of our method in image classification, and the results demonstrate that weight similarity evaluation works for other frameworks and tasks.

Federated learning allows multiple parties to train models while jointly protecting user privacy. However, traditional federated learning requires each client to have the same model structure to fuse the global model. In real-world scenarios, each client may need to develop personalized models based on its environment, making it difficult to perform federated learning in a heterogeneous model environment. Some knowledge distillation methods address the problem of heterogeneous model fusion to some extent. However, these methods assume that each client is trustworthy. Some clients may produce malicious or low-quality knowledge, making it difficult to aggregate trustworthy knowledge in a heterogeneous environment. To address these challenges, we propose a trustworthy heterogeneous federated learning framework (FedTKD) to achieve client identification and trustworthy knowledge fusion. Firstly, we propose a malicious client identification method based on client logit features, which can exclude malicious information in fusing global logit. Then, we propose a selectivity knowledge fusion method to achieve high-quality global logit computation. Additionally, we propose an adaptive knowledge distillation method to improve the accuracy of knowledge transfer from the server side to the client side. Finally, we design different attack and data distribution scenarios to validate our method. The experiment shows that our method outperforms the baseline methods, showing stable performance in all attack scenarios and achieving an accuracy improvement of 2% to 3% in different data distributions.