In recent years, knowledge graph completion (KGC) models based on pre-trained language model (PLM) have shown promising results. However, the large number of parameters and high computational cost of PLM models pose challenges for their application in downstream tasks. This paper proposes a progressive distillation method based on masked generation features for KGC task, aiming to significantly reduce the complexity of pre-trained models. Specifically, we perform pre-distillation on PLM to obtain high-quality teacher models, and compress the PLM network to obtain multi-grade student models. However, traditional feature distillation suffers from the limitation of having a single representation of information in teacher models. To solve this problem, we propose masked generation of teacher-student features, which contain richer representation information. Furthermore, there is a significant gap in representation ability between teacher and student. Therefore, we design a progressive distillation method to distill student models at each grade level, enabling efficient knowledge transfer from teachers to students. The experimental results demonstrate that the model in the pre-distillation stage surpasses the existing state-of-the-art methods. Furthermore, in the progressive distillation stage, the model significantly reduces the model parameters while maintaining a certain level of performance. Specifically, the model parameters of the lower-grade student model are reduced by 56.7\% compared to the baseline.
Auditory Attention Detection (AAD) aims to detect target speaker from brain signals in a multi-speaker environment. Although EEG-based AAD methods have shown promising results in recent years, current approaches primarily rely on traditional convolutional neural network designed for processing Euclidean data like images. This makes it challenging to handle EEG signals, which possess non-Euclidean characteristics. In order to address this problem, this paper proposes a dynamical graph self-distillation (DGSD) approach for AAD, which does not require speech stimuli as input. Specifically, to effectively represent the non-Euclidean properties of EEG signals, dynamical graph convolutional networks are applied to represent the graph structure of EEG signals, which can also extract crucial features related to auditory spatial attention in EEG signals. In addition, to further improve AAD detection performance, self-distillation, consisting of feature distillation and hierarchical distillation strategies at each layer, is integrated. These strategies leverage features and classification results from the deepest network layers to guide the learning of shallow layers. Our experiments are conducted on two publicly available datasets, KUL and DTU. Under a 1-second time window, we achieve results of 90.0\% and 79.6\% accuracy on KUL and DTU, respectively. We compare our DGSD method with competitive baselines, and the experimental results indicate that the detection performance of our proposed DGSD method is not only superior to the best reproducible baseline but also significantly reduces the number of trainable parameters by approximately 100 times.
Numerous studies have affirmed that deep learning models can facilitate early diagnosis of lesions in endoscopic images. However, the lack of available datasets stymies advancements in research on nasal endoscopy, and existing models fail to strike a good trade-off between model diagnosis performance, model complexity and parameters size, rendering them unsuitable for real-world application. To bridge these gaps, we created the first large-scale nasal endoscopy dataset, named 7-NasalEID, comprising 11,352 images that contain six common nasal diseases and normal samples. Subsequently, we proposed U-SEANNet, an innovative U-shaped architecture, underpinned by depth-wise separable convolution. Moreover, to enhance its capacity for detecting nuanced discrepancies in input images, U-SEANNet employs the Global-Local Channel Feature Fusion module, enabling it to utilize salient channel features from both global and local contexts. To demonstrate U-SEANNet's potential, we benchmarked U-SEANNet against seventeen modern architectures through five-fold cross-validation. The experimental results show that U-SEANNet achieves a commendable accuracy of 93.58%. Notably, U-SEANNet's parameters size and GFLOPs are only 0.78M and 0.21, respectively. Our findings suggest U-SEANNet is the state-of-the-art model for nasal diseases diagnosis in endoscopic images.
Ultrasound imaging serves as a pivotal tool for diagnosing cervical lymph node lesions. However, the diagnoses of these images largely hinge on the expertise of medical practitioners, rendering the process susceptible to misdiagnoses. Although rapidly developing deep learning has substantially improved the diagnoses of diverse ultrasound images, there remains a conspicuous research gap concerning cervical lymph nodes. The objective of our work is to accurately diagnose cervical lymph node lesions by leveraging a deep learning model. To this end, we first collected 3392 images containing normal lymph nodes, benign lymph node lesions, malignant primary lymph node lesions, and malignant metastatic lymph node lesions. Given that ultrasound images are generated by the reflection and scattering of sound waves across varied bodily tissues, we proposed the Conv-FFT Block. It integrates convolutional operations with the fast Fourier transform to more astutely model the images. Building upon this foundation, we designed a novel architecture, named US-SFNet. This architecture not only discerns variances in ultrasound images from the spatial domain but also adeptly captures microstructural alterations across various lesions in the frequency domain. To ascertain the potential of US-SFNet, we benchmarked it against 12 popular architectures through five-fold cross-validation. The results show that US-SFNet is SOTA and can achieve 92.89% accuracy, 90.46% precision, 89.95% sensitivity and 97.49% specificity, respectively.
Utilizing deep learning (DL) models to improve the early diagnosis of nasal diseases from nasal endoscopic images holds paramount importance. However, the lack of available datasets stymies advancements in this field. Furthermore, existing models fail to strike a good trade-off between model diagnosis performance, model complexity and parameter size, rendering them unsuitable for practical application. To bridge these gaps, we created the first large-scale nasal endoscopy dataset, named 7-NasEID, comprising 11,352 images that span six nasal diseases and normal samples. Building on this, we proposed U-SEANNet, an innovative architecture, underpinned by depth-wise separable convolutions. Additionally, to augment its discernment capabilities for subtle variations in input images, we further proposed the Global-Local Channel Feature Fusion Module, enabling the U-SEANNet to focus salient channel features from both global and local contexts. Notably, U-SEANNet's parameter size and GFLOPs are only 0.78M and 0.21, respectively. Employing the 7-NasalEID, we conducted the five-fold cross-validation on U-SEANNet, juxtaposing its performance against seventeen renowned architectures. The experimental results suggest U-SEANNet as the state-of-the-art (SOTA) model, achieves an accuracy of 93.58%, sensitivity of 90.17%, and specificity of 91.27%. These findings demonstrate U-SEANNet's prodigious potential for diagnosing nasal diseases in practical use, providing the development of efficacy nasal diseases diagnosis tools with a new insight.
The rhythm of synthetic speech is usually too smooth, which causes that the fundamental frequency (F0) of synthetic speech is significantly different from that of real speech. It is expected that the F0 feature contains the discriminative information for the fake speech detection (FSD) task. In this paper, we propose a novel F0 subband for FSD. In addition, to effectively model the F0 subband so as to improve the performance of FSD, the spatial reconstructed local attention Res2Net (SR-LA Res2Net) is proposed. Specifically, Res2Net is used as a backbone network to obtain multiscale information, and enhanced with a spatial reconstruction mechanism to avoid losing important information when the channel group is constantly superimposed. In addition, local attention is designed to make the model focus on the local information of the F0 subband. Experimental results on the ASVspoof 2019 LA dataset show that our proposed method obtains an equal error rate (EER) of 0.47% and a minimum tandem detection cost function (min t-DCF) of 0.0159, achieving the state-of-the-art performance among all of the single systems.
In this paper, we propose the multi-perspective information fusion (MPIF) Res2Net with random Specmix for fake speech detection (FSD). The main purpose of this system is to improve the model's ability to learn precise forgery information for FSD task in low-quality scenarios. The task of random Specmix, a data augmentation, is to improve the generalization ability of the model and enhance the model's ability to locate discriminative information. Specmix cuts and pastes the frequency dimension information of the spectrogram in the same batch of samples without introducing other data, which helps the model to locate the really useful information. At the same time, we randomly select samples for augmentation to reduce the impact of data augmentation directly changing all the data. Once the purpose of helping the model to locate information is achieved, it is also important to reduce unnecessary information. The role of MPIF-Res2Net is to reduce redundant interference information. Deceptive information from a single perspective is always similar, so the model learning this similar information will produce redundant spoofing clues and interfere with truly discriminative information. The proposed MPIF-Res2Net fuses information from different perspectives, making the information learned by the model more diverse, thereby reducing the redundancy caused by similar information and avoiding interference with the learning of discriminative information. The results on the ASVspoof 2021 LA dataset demonstrate the effectiveness of our proposed method, achieving EER and min-tDCF of 3.29% and 0.2557, respectively.
In this paper, we propose a novel self-distillation method for fake speech detection (FSD), which can significantly improve the performance of FSD without increasing the model complexity. For FSD, some fine-grained information is very important, such as spectrogram defects, mute segments, and so on, which are often perceived by shallow networks. However, shallow networks have much noise, which can not capture this very well. To address this problem, we propose using the deepest network instruct shallow network for enhancing shallow networks. Specifically, the networks of FSD are divided into several segments, the deepest network being used as the teacher model, and all shallow networks become multiple student models by adding classifiers. Meanwhile, the distillation path between the deepest network feature and shallow network features is used to reduce the feature difference. A series of experimental results on the ASVspoof 2019 LA and PA datasets show the effectiveness of the proposed method, with significant improvements compared to the baseline.
Recently, pioneer research works have proposed a large number of acoustic features (log power spectrogram, linear frequency cepstral coefficients, constant Q cepstral coefficients, etc.) for audio deepfake detection, obtaining good performance, and showing that different subbands have different contributions to audio deepfake detection. However, this lacks an explanation of the specific information in the subband, and these features also lose information such as phase. Inspired by the mechanism of synthetic speech, the fundamental frequency (F0) information is used to improve the quality of synthetic speech, while the F0 of synthetic speech is still too average, which differs significantly from that of real speech. It is expected that F0 can be used as important information to discriminate between bonafide and fake speech, while this information cannot be used directly due to the irregular distribution of F0. Insteadly, the frequency band containing most of F0 is selected as the input feature. Meanwhile, to make full use of the phase and full-band information, we also propose to use real and imaginary spectrogram features as complementary input features and model the disjoint subbands separately. Finally, the results of F0, real and imaginary spectrogram features are fused. Experimental results on the ASVspoof 2019 LA dataset show that our proposed system is very effective for the audio deepfake detection task, achieving an equivalent error rate (EER) of 0.43%, which surpasses almost all systems.