Advanced automatic pronunciation error detection (APED) algorithms are usually based on state-of-the-art automatic speech recognition (ASR) techniques. With the development of deep learning technology, end-to-end ASR technology has gradually matured and achieved positive practical results, which provides us with a new opportunity to update the APED algorithm. We first constructed an end-to-end ASR system based on the hybrid connectionist temporal classification and attention (CTC/attention) architecture. An adaptive parameter was used to enhance the complementarity of the connectionist temporal classification (CTC) model and the attention-based seq2seq model, further improving the performance of the ASR system. After this, the improved ASR system was used in the APED task of Mandarin, and good results were obtained. This new APED method makes force alignment and segmentation unnecessary, and it does not require multiple complex models, such as an acoustic model or a language model. It is convenient and straightforward, and will be a suitable general solution for L1-independent computer-assisted pronunciation training (CAPT). Furthermore, we find that in regards to accuracy metrics, our proposed system based on the improved hybrid CTC/attention architecture is close to the state-of-the-art ASR system based on the deep neural network–deep neural network (DNN–DNN) architecture, and has a stronger effect on the F-measure metrics, which are especially suitable for the requirements of the APED task.

The judgment of facade styles is an important part of the sustainable utilization and restorative process of historical architectures. Contemporary Harbin needs the help of modern architectural facade forms in the planning of the famous historic city, especially with the facade renovation of old architectures with non-cultural heritage. This paper discusses the possibility of applying advanced image recognition algorithms to the classification of the modern Harbin architectural facade styles and argues that the keys to the classification and positioning of the styles are the forms, the details, and the decorative patterns of the architectural facades, together with the deformation and the quantitative variation factors of the facade decoration symbols. Based on the conventional classification method, the facade styles of Harbin modern architecture were divided into 12 categories after data analysis. To better capture the overall structure information and the style features of the local components in the architectural images, the group convolution and the dilated convolution were added into the ResNet model, and then, the improved channel attention mechanism was introduced to construct a novel CA-MSResNet model. The CA-MSResNet model could more accurately identify the morphological elements and the style categories of the architectures, and the average accuracy reached 87.5%. These techniques, with their promising results, are expected to be further applied in the future research on the sustainable utilization and renovation of Harbin modern architecture.

This work aims to address the image classification problem under open-set protocol: classes in test set do not appear in the training set. Intuitively, convolutional Neural Network (CNN) with softmax loss is a straight-forward solution. However, the unknown class (is not predefined in the training set) makes the boundaries of intra-class and inter-class more blurred, which brings more challenges for image classification. Although some softmax variants, such as center loss, CosFace loss etc., focus on learning discriminative features by minimizing the intra-class distance, they do not explicitly maximize inter-class distance, which is more important for open-set problem verified by our experiments. Besides, even though deep metric learning, such as with the contrastive loss and the triplet loss, can learn discriminative features of intra-class and inter-class, it needs a time-consuming image sampling process during training. In this paper, we propose a novel normalized maximal margin (NMM) loss for open-set image classification, which not only explicitly minimizes intra-class distance and maximizes inter-class distance, but also defines their margins. Specially, after analyzing the advantage of angular space that the softmax loss normalized by the feature and weights through geometric interpretation, we make NMM work in angular space. Then, the validity of NMM for discriminative features learning is demonstrated from the view of geometric interpretation as well. After that, we innovatively determine the upper bound of inter-class margin by theoretical analysis. Finally, extensive experiments are conducted on popular datasets: CIFAR-100 (object recognition), ImageNet (image classification), LFW (face recognition) and MSMT17 (person re-identification) to verify the effectiveness of NMM. The experimental results show that NMM achieves very competitive performance.

Extracting richer emotional representations from raw speech is one of the key approaches to improving the accuracy of Speech Emotion Recognition (SER). In recent years, there has been a trend in utilizing self-supervised learning (SSL) for extracting SER features, due to the exceptional performance of SSL in Automatic Speech Recognition (ASR). However, existing SSL methods are not sufficiently sensitive in capturing emotional information, making them less effective for SER tasks. To overcome this issue, this study proposes MS-EmoBoost, a novel strategy for enhancing self-supervised speech emotion representations. Specifically, MS-EmoBoost uses the deep emotional information from Melfrequency cepstral coefficient (MFCC) and spectrogram as guidance to enhance the emotional representation capabilities of self-supervised features. To determine the effectiveness of our proposed approach, we conduct a comprehensive experiment on three benchmark speech emotion datasets: IEMOCAP, EMODB, and EMOVO. The SER performance is measured by weighted accuracy (WA) and unweighted accuracy (UA). The experimental results show that our method successfully enhances the emotional representation capability of wav2vec 2.0 Base features, achieving competitive performance in SER tasks (IEMOCAP:WA,72.10%; UA,72.91%; EMODB:WA,92.45%; UA,92.62%; EMOVO:WA,86.88%; UA,87.51%), and proves effective for other self-supervised features.

Sustainable tourist route design is a critical challenge in industrial heritage planning. While prior tourism routing algorithms predominantly minimize physical distance, and conventional heritage planning focuses on the static preservation of abandoned sites, both lack the multi-objective adaptability required for “living” industrial landscapes. In such dynamic environments, active production, tourism, and ecological conservation intricately coexist. To address this gap, this study proposes a novel, data-driven route planning framework, taking the Tianjin Changlu Salt Field as a case study. The genuine novelty lies in integrating multi-objective network optimization with spatial design implementation. The site is abstracted into a topological network comprising 13 nodes and 19 edges. Multi-attribute edge weights—incorporating spatial distance, travel time, landscape attractiveness, and ecological sensitivity—are quantified using entropy weighting fused with subjective preferences. Using the Floyd–Warshall algorithm, three theme-based touring routes are generated. Unlike traditional methods, this workflow actively translates algorithmic outputs into concrete spatial strategies, such as bypassing ecologically sensitive zones and transforming production facilities into perceptible landscape nodes. Comparative evaluations demonstrate that these optimized routes achieve higher comprehensive utility than baseline and designer-generated schemes, offering a pioneering, reproducible paradigm for the sustainable renewal of living industrial heritage.