Audio deepfake detection (ADD) aims to verify the authenticity of audio. However, its performance declines sharply when facing significant domain discrepancies caused by unknown datasets. Unsupervised domain adaptation (UDA) has been applied to mitigate domain mismatch. However, as generative models evolve, existing UDA methods struggle with catastrophic forgetting when facing continuously emerging spoofing methods. To address this challenge, we introduce continual UDA for ADD, which involves sequentially training across multiple target domains with continual learning. We propose a causality-distillation-based continual domain adversarial training framework for continual UDA, called CD-DAT. Specifically, we employ the domain adversarial training (DAT) framework to learn both spoofing-discriminative and domain-invariant deep features. In addition, we design a continual learning algorithm utilizing causality distillation to capture the mapping between utterances and classes, effectively mitigating forgetting and maintaining generalization. Experiments demonstrated that CD-DAT improved detection performance across all domains, confirming its memory stability and learning plasticity.

In recent years, semi-supervised 3D medical image segmentation has gained significant attention. However, current methods often struggle with multi-scale voxel differences and overlook the importance of loss weight balancing. To address these issues, we propose an adaptive multi-scale local correction method (AMLC). Our key contributions are: (1) a multi-scale local correction module to accurately capture differences between 3D voxel blocks at various scales; (2) an adaptive weighting adjustment module that dynamically balances losses, improving robustness and training. Experiments show that AMLC significantly outperforms existing methods on the public dataset, demonstrating its effectiveness.

In recent years, numerous studies have demonstrated a close connection between human diseases and the regulation of non-coding RNAs (ncRNAs). Predicting potential ncRNAs associated with disease can help provide critical information for diagnosis and treatment of disease, leading to better disease analysis and prevention. Building good algorithms for predicting associations between ncRNAs and disease is critical. Many current algorithms have poor performance in identifying the association between ncRNAs and diseases. As a method for predicting the association between ncRNAs and diseases, we develop a Matrix Factorization method based on the Correntropy Induced Loss (C-loss) function (C-lossMF). In our model, we first construct ncRNA similarity matrix and disease similarity matrix by considering some important similarity information, and extract effective information of ncRNA and disease from them. Next, we perform matrix decomposition of ncRNA-disease association matrix and apply $L2$ loss and C-loss. Then we add collaborative regularization of RNA similarity matrix and the collaborative regularization of disease similarity matrix to take full advantage of the information in the similarity matrix. In particular, we propose a method that combines semi-quadratic optimization and gradient descent to optimize the model. In the experiments, we utilize the five-fold cross validation method on four datasets to evaluate the performance of C-lossMF. Comparing this model with other advanced models, the results show that it performs better.

Audio anti-spoofing algorithms struggle with fake samples from unseen spoofing techniques, even when trained with diverse data sets or data augmentation strategies. Unsupervised domain adaptation (UDA) algorithms have the potential to mitigate this challenge. Typically, UDA assumes that the source and target domains are distinct distributions with clear boundaries and seeks to align model representations between them. However, in anti-spoofing, various spoofing algorithms could cause the distributions of the generated samples to overlap, resulting in unclear domain boundaries. This hinders UDA algorithms from effectively measuring and aligning domain discrepancies. Moreover, forcibly aligning samples with significant discrepancies could diminish the model’s discriminative capability. To solve this problem, we propose a domain attention algorithm with optimal transport (OT), termed Sinkhorn Domain Attention (SHDA). Unlike traditional attention mechanisms, SHDA identifies the optimal transfer plan by analyzing the global probability differences among cross-domain samples. Specifically, we first extract audio representations from various domains to compute the overall cost matrix between the source and target domains. Next, we employ Sinkhorn’s iteration to calculate the OT coupling matrix, where cross-domain samples with minor differences receive higher transfer weights, while those with substantial differences receive lower weights. Finally, we use the coupling and cost matrices to compute the adaptation loss, effectively transferring the anti-spoofing model from multiple sources to the target domain. We conducted eight cross-domain experiments using eleven well-known anti-spoofing corpora. The results indicate that our label-free SHDA surpassed the state-of-the-art model by 40%.

Autism is a neurodevelopmental disorder characterized by difficulties in social interaction, communication, and sensory sensitivity. Functional magnetic resonance imaging (fMRI) is a commonly used brain imaging technique to obtain functional connectivity information in individuals with autism. However, the heterogeneity of functional MRI data from different imaging centers poses a modeling challenge, and the lack of interpretability in the models hinders the identification of biomarkers. To address these issues, this study proposes a deep learning model based on a dynamic functional connectivity matrix that extracts shared features across multiple centers, mitigates the multicentre problem, enhances the representation of the data, and combines features from multiple pathways to capture a comprehensive view of brain connectivity patterns. In addition, two complementary approaches are designed to enhance the interpretability of the model and further explore the presence of biomarkers by analyzing changes in important features of the model. The code will be released soon.

In the tasks of domain adaptation (DA) for speech emotion recognition (SER), self-supervised learning (SSL) algorithms could effectively explore domain and structural information from target domain samples, thereby mitigating domain discrepancies. However, in a general setting, when the target domain contains emotions that are never observed in the source domain, namely in open-set DA, existing SSL-based DA methods cannot maintain the robustness because of the interference of the extra unknown classes. To address this challenge, we propose the self-supervised domain exploration with an optimal transport (OT) regularization (SDEOTR) algorithm. First, we integrate the SSL algorithm into the SER model to mitigate the domain differences. Further, we categorize target domain samples into known and unknown groups based on the network’s prediction confidence. Finally, we employ OT to maximize the global probability distance between the two groups, aiming to decrease the impact of unknown emotions on the SER model. Cross-domain SER experimental results showed that our label-free SDEOTR significantly improved the performance of existing adaptive SER algorithms in open-set scenarios.

Automatic speaker verification (ASV) systems face significant challenges when exposed to spoofing attacks, necessitating robust countermeasures. In this work, we focus on the source speaker verification (SSV) task, which aims to identify the source speaker hidden in spoofed speech generated by voice conversion (VC) systems. We propose a distillation-based feature extraction algorithm to enhance the model’s ability to verify source speakers. Our method employs a pretraining ASV model as a teacher network and the SSV model as a student network, using bona fide speech to guide the learning process. However, the improvements were marginal, particularly on the development set, indicating the complexity and resource demands of fine-tuning the distillation parameters. Our findings underscore the inherent difficulties in SSV and highlight the need for further research to develop more effective solutions. Besides, our submission won fourth place in the 2024 Source Speaker Tracking Challenge.

Medical image segmentation is a critical task in the healthcare field. While deep learning techniques have shown promise in this area, they often require a large number of accurately labeled images. To address this issue, semisupervised learning has emerged as a potential solution by reducing the reliance on precise annotations. Among these approaches, the student-teacher framework has garnered attention, but it is limited in its reliance solely on the teacher model for information. To overcome this limitation, we propose a prototype-based mutual consistency learning (PMCL) framework. This framework utilizes two branches that learn from each other, incorporating supervision loss and consistency loss to adapt to minor data perturbations and structural differences. By employing prototype consistency learning, we are able to achieve reliable consistency loss. Our experiments on three public medical image datasets demonstrate that PMCL outperforms other state-of-the-art methods, indicating its potential in semisupervised medical image segmentation. Our framework has the potential to assist medical professionals in enhancing their diagnoses and delivering improved patient care.

Cross-domain speaker recognition (SR) can be improved by unsupervised domain adaptation (UDA) algorithms. UDA algorithms often reduce domain mismatch at the cost of decreasing the discrimination of speaker features. In contrast, optimal transport (OT) has the potential to achieve domain alignment while preserving the speaker discrimination capability in UDA applications; however, naively applying OT to measure global probability distribution discrepancies between the source and target domains may induce negative transports where samples belonging to different speakers are coupled in transportation. These negative transports reduce the SR model's discriminative power, degrading the SR performance. This paper proposes a coupling-regularized optimal transport (CROT) algorithm for cross-domain SR to reduce the negative transport during UDA. In the proposed CROT, two consecutive processing modules regularize the coupling paths for the OT solution: a progressive inter-speaker constraint (PISC) module and a coupling-smoothed regularization (CSR) module. The PISC, designed as a pseudo-label memory bank with curriculum learning, is first applied to select valid samples to guarantee that coupling samples are from the same speaker. The CSR, designed to control the information entropy of the coupling paths further, reduces the effect of negative transport in UDA. To evaluate the effectiveness of the proposed algorithm, cross-domain SR experiments were conducted under different target domains, speaker encoders, corpora, and acoustic features. Experimental results showed that CROT achieved a 50% relative reduction in equal error rates compared to conventional OT-based UDAs, outperforming the state-of-the-art UDAs.

Optimal transport (OT) can be applied to cross-domain adaptation in speaker verification (SV) by converting speakers' probability distributions from source to target domains. However, in scenarios involving over-massive categories (speakers) or difficult samples in discrimination, OT often has difficulty computing effective transports. To address this challenge, we propose an OT-based unsupervised domain adaptation (UDA) framework for SV, OT with a diversified memory bank, called DMB-OT, which ensures the accuracy of transfers by two strategies: (1) It regularizes the solution space of OT, which attempts to plan transformations between audio samples from the same speaker with high confidence; (2) it integrates a dynamic curriculum learning algorithm, preventing OT from calculating transport couplings based on hard-discriminative samples in the early stage of UDA. Experiments under different target domains showed that our unsupervised DMB-OT could significantly improve the performance of OT-based UDA and could even match the performance of the supervised PLDA-based adaptation.

Automatic speaker verification (ASV) systems, which determine whether two speeches are from the same speaker, mainly focus on verification accuracy while ignoring inference speed. However, in real applications, both inference speed and verification accuracy are essential. This study proposes cross-sequential re-parameterization (CS-Rep), a novel topology re-parameterization strategy for multi-type networks, to increase the inference speed and verification accuracy of models. CS-Rep solves the problem that existing re-parameterization methods are not suitable for typical ASV backbones. When a model applies CS-Rep, the training-period network utilizes a multi-branch topology to capture speaker information, whereas the inference-period model converts to a time-delay neural network (TDNN)-like plain backbone with stacked TDNN layers to achieve the fast inference speed. Based on CS-Rep, an improved TDNN with friendly test and deployment called Rep-TDNN is proposed. Compared with the state-of-the-art model ECAPA-TDNN, Rep-TDNN increases the actual inference speed by about 50% and reduces the EER by 10%. The code and trained models are available at https://github.com/zrtlemontree/CS-Rep.

Accurate tumor segmentation of tumor images can assist doctors to diagnose diseases. However, achieving very high precision in tumor segmentation requires a large amount of annotated data, which is not easy for medical image data. In this paper, we present a novel double noise mean teacher self-ensembling model for semi-supervised 2D tumor segmentation. Concretely, the network is serialized by two groups of student-teacher networks. We design an auxiliary student-teacher module to learn the consistency regularity between the unlabeled image feature maps. In order to improve the robustness of the network, we add the random Gaussian noise to the student model every time the teacher model is updated. We test our model on the small cell lung tumor dataset and CVC-ClinicDB, and our model achieves the performance of nearly fully supervised segmentation. Moreover, the performance of our method outperforms the existing semi-supervised methods in four indicators.

MOTIVATION: Metabolomics has developed rapidly in recent years, and metabolism-related databases are also gradually constructed. Nowadays, more and more studies are being carried out on diverse microbes, metabolites and diseases. However, the logics of various associations among microbes, metabolites and diseases are limited understanding in the biomedicine of gut microbial system. The collection and analysis of relevant microbial bioinformation play an important role in the revelation of microbe-metabolite-disease associations. Therefore, the dataset that integrates multiple relationships and the method based on complex heterogeneous graphs need to be developed. RESULTS: In this study, we integrated some databases and extracted a variety of associations data among microbes, metabolites and diseases. After obtaining the three interconnected bilateral association data (microbe-metabolite, metabolite-disease and disease-microbe), we considered building a heterogeneous graph to describe the association data. In our model, microbes were used as a bridge between diseases and metabolites. In order to fuse the information of disease-microbe-metabolite graph, we used the bipartite graph attention network on the disease-microbe and metabolite-microbe bipartite graph. The experimental results show that our model has good performance in the prediction of various disease-metabolite associations. Through the case study of type 2 diabetes mellitus, Parkinson's disease, inflammatory bowel disease and liver cirrhosis, it is noted that our proposed methodology are valuable for the mining of other associations and the prediction of biomarkers for different human diseases.Availability and implementation: https://github.com/Selenefreeze/DiMiMe.git.

Current human biomedical research shows that human diseases are closely related to non-coding RNAs, so it is of great significance for human medicine to study the relationship between diseases and non-coding RNAs. Current research has found associations between non-coding RNAs and human diseases through a variety of effective methods, but most of the methods are complex and targeted at a single RNA or disease. Therefore, we urgently need an effective and simple method to discover the associations between non-coding RNAs and human diseases. In this paper, we propose a sparse regularized joint projection model (SRJP) to identify the associations between non-coding RNAs and diseases. First, we extract information through a series of ncRNA similarity matrices and disease similarity matrices and assign average weights to the similarity matrices of the two sides. Then we decompose the similarity matrices of the two spaces into low-rank matrices and put them into SRJP. In SRJP, we innovatively use the projection matrix to combine the ncRNA side and the disease side to identify the associations between ncRNAs and diseases. Finally, the regularization term in SRJP effectively improves the robustness and generalization ability of the model. We test our model on different datasets involving three types of ncRNAs: circRNA, microRNA and long non-coding RNA. The experimental results show that SRJP has superior ability to identify and predict the associations between ncRNAs and diseases.

Zero-shot voice conversion (VC) where both source and target speakers are unseen in the training dataset has become a new research direction. Using speaker embeddings instead of one-hot vectors to represent speaker identity is a key point, which makes VC models work on unseen speakers. In our work, a newly designed neural network was used to adjust the speaker embeddings of unseen speakers. This enables speaker embeddings to perform better on zero-shot VC. In addition, disentangled representation of features is the mainstream method to achieve zero-shot VC. In terms of input features of VC model, we use Mel-cepstral and F0 as simple acoustic features (SAF) rather than Mel-spectrograms. This avoids F0 conflicts in decoder that existed in the previous methods. The evaluations demonstrate that our proposed methods improve the quality of converted speech in terms of naturalness and similarity.

In addition to biological plausibility, spiking neural networks (SNNs) are drawing significant attention recently due to their promising advantages in computational efficiency, which could potentially help to overcome the consumption obstacle in deep learning. Training deep SNNs is of great importance for solving practical tasks. In this paper, we propose a new deep spike learning rule to train deep SNNs to associate input spike patterns with desired output spike numbers. Our proposed rule is able to construct error signals based on a critical time point that is likely close to change the neuron's response toward its desired. We evaluate the performance of our method with both static and dynamic vision datasets. Experimental results show that the proposed rule can effectively learn spike patterns encoded with both rate and temporal codes, and more importantly, achieves impressive accuracies on all benchmark datasets. We further provide a comprehensive analysis of both codes with respect to efficiency and robustness. Our study thus provides an effective rule that is generalized to process information under a broad range of coding schemes, which would be of great merit for spike-based learning and processing.

Spiking neural networks (SNNs) are promising to replicate the efficiency of the brain by utilizing a paradigm of spike-based computation. Training a deep SNN is of great importance for solving practical tasks as well as discovering the fascinating capability of spike-based computation. The biologically plausible scheme of local learning motivates many approaches that enable training deep networks in an efficient parallel way. However, most of the existing spike-based local learning approaches show relatively low performances on challenging tasks. In this paper, we propose a new spike-based temporal dependent local learning (TDLL) algorithm, where each hidden layer of a deep SNN is independently trained with an auxiliary trainable spiking projection layer, and temporal dependency is fully employed to construct local errors for adjusting parameters. We examine the performance of the proposed TDLL with various networks on the MNIST, Fashion-MNIST, SVHN and CIFAR-10 datasets. Experimental results highlight that our method can scale up to larger networks, and more importantly, achieves relatively high accuracies on all benchmarks, which are even competitive with the ones obtained by global backpropagation-based methods. This work therefore contributes to providing an effective and efficient local learning method for deep SNNs, which could greatly benefit the developments of distributed neuromorphic computing.

With the development of high-throughput sequencing technology, the genomic sequences increased exponentially over the last decade. In order to decode these new genomic data, machine learning methods were introduced for genome annotation and analysis. Due to the requirement of most machines learning methods, the biological sequences must be represented as fixed-length digital vectors. In this representation procedure, the physicochemical properties of k-tuple nucleotides are important information. However, the values of the physicochemical properties of k-tuple nucleotides are scattered in different resources. To facilitate the studies on genomic sequences, we developed the first comprehensive database, namely KNIndex (https://knindex.pufengdu.org), for depositing and visualizing physicochemical properties of k-tuple nucleotides. Currently, the KNIndex database contains 182 properties including one for mononucleotide (DNA), 169 for dinucleotide (147 for DNA and 22 for RNA) and 12 for trinucleotide (DNA). KNIndex database also provides a user-friendly web-based interface for the users to browse, query, visualize and download the physicochemical properties of k-tuple nucleotides. With the built-in conversion and visualization functions, users are allowed to display DNA/RNA sequences as curves of multiple physicochemical properties. We wish that the KNIndex will facilitate the related studies in computational biology.

The functional magnetic resonance imaging (fMRI) is a noninvasive technique for studying brain activity, such as brain network analysis, neural disease automated diagnosis and so on. However, many existing methods have some drawbacks, such as limitations of graph theory, lack of global topology characteristic, local sensitivity of functional connectivity, and absence of temporal or context information. In addition to many numerical features, fMRI time series data also cover specific contextual knowledge and global fluctuation information. Here, we propose multi-scale time-series kernel-based learning model for brain disease diagnosis, based on Jensen-Shannon divergence. First, we calculate correlation value within and between brain regions over time. In addition, we extract multi-scale synergy expression probability distribution (interactional relation) between brain regions. Also, we produce state transition probability distribution (sequential relation) on single brain regions. Then, we build time-series kernel-based learning model based on Jensen-Shannon divergence to measure similarity of brain functional connectivity. Finally, we provide an efficient system to deal with brain network analysis and neural disease automated diagnosis. On Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, our proposed method achieves accuracy of 0.8994 and AUC of 0.8623. On Major Depressive Disorder (MDD) dataset, our proposed method achieves accuracy of 0.9166 and AUC of 0.9263. Experiments show that our proposed method outperforms other existing excellent neural disease automated diagnosis approaches. It shows that our novel prediction method performs great accurate for identification of brain diseases as well as existing outstanding prediction tools.

Abstract Background Protein-protein interaction plays a key role in a multitude of biological processes, such as signal transduction, de novo drug design, immune responses, and enzymatic activities. Gaining insights of various binding abilities can deepen our understanding of the interaction. It is of great interest to understand how proteins in a complex interact with each other. Many efficient methods have been developed for identifying protein-protein interface. Results In this paper, we obtain the local information on protein-protein interface, through multi-scale local average block and hexagon structure construction. Given a pair of proteins, we use a trained support vector regression (SVR) model to select best configurations. On Benchmark v4.0, our method achieves average Irmsd value of 3.28Å and overall Fnat value of 63%, which improves upon Irmsd of 3.89Å and Fnat of 49% for ZRANK, and Irmsd of 3.99Å and Fnat of 46% for ClusPro. On CAPRI targets, our method achieves average Irmsd value of 3.45Å and overall Fnat value of 46%, which improves upon Irmsd of 4.18Å and Fnat of 40% for ZRANK, and Irmsd of 5.12Å and Fnat of 32% for ClusPro. The success rates by our method, FRODOCK 2.0, InterEvDock and SnapDock on Benchmark v4.0 are 41.5%, 29.0%, 29.4% and 37.0%, respectively. Conclusion Experiments show that our method performs better than some state-of-the-art methods, based on the prediction quality improved in terms of CAPRI evaluation criteria. All these results demonstrate that our method is a valuable technological tool for identifying protein-protein interface.