基于层次化Conformer的语音合成

语音合成需要将输入语句的文本转换为包含音素、单词和语句的语音信号。现有语音合成方法将语句看作一个整体,难以准确地合成出不同长度的语音信号。通过分析语音信号中蕴含的层次化关系,分别设计基于Conformer的层次化文本编码器和基于Conformer的层次化语音编码器,并提出了一种基于层次化文本-语音Conformer的语音合成模型。首先,该模型根据输入文本信号的长度,构建层次化文本编码器,包括音素级、单词级、语句级文本编码器3个层次,不同层次的文本编码器描述不同长度的文本信息;并使用Conformer的注意力机制来学习该长度信号中不同时间特征之间的关系。利用层次化的文本编码器,能够找出语句中不同长度需要强调的信息,有效实现不同长度的文本特征提取,缓解合成的语音信号持续时间长度不确定的问题。其次,层次化语音编码器包括音素级、单词级、语句级语音编码器3个层次。每个层次的语音编码器将文本特征作为Conformer的查询向量,将语音特征作为Conformer的关键字向量和值向量,来提取文本特征和语音特征的匹配关系。利用层次化的语音编码器和文本语音匹配关系,可以缓解不同长度语音信号合成不准确的问题。所提模型的层次化文本-语音编码器可以灵活地嵌入现有的多种解码器中,通过文本和语音之间的互补,提供更为可靠的语音合成结果。在LJSpeech和LibriTTS两个数据集上进行实验验证,实验结果表明,所提方法的梅尔倒谱失真小于现有语音合成方法。

基于改进Conformer的新闻领域端到端语音识别

目前,开源的中文语音识别数据集大多面向通用领域,缺少面向新闻领域的开源语音识别语料库,因此该文构建了面向新闻领域的中文语音识别数据集CH_NEWS_ASR,并使用ESPNET-0.9.6框架的RNN、Transformer和Conformer等模型对数据集的有效性进行了验证,实验表明,该文所构建的语料在最好的模型上CER为4.8%,SER为39.4%。由于新闻联播主持人说话语速相对较快,该文构建的数据集文本平均长度为28个字符,是Aishell_1数据集文本平均长度的2倍;且以往的研究中训练目标函数通常为基于字或词水平,缺乏明确的句子水平关系,因此该文提出了一个句子层级的一致性模块,与Conformer模型结合,直接减少源语音和目标文本的表示差异,在开源的Aishell_1数据集上其CER降低0.4%,SER降低2%;在CH_NEWS_ASR数据集上其CER降低0.9%,SER降低3%,实验结果表明,该方法在不增加模型参数量的前提下能有效提升语音识别的质量。

基于Conformer的端到端语音识别方法

针对Conformer编码器的声学输入网络对FBank语音信息提取不足和通道特征信息缺失问题,提出一种RepVGG-SE-Conformer的端到端语音识别方法。首先,利用RepVGG的多分支结构,增强模型的语音信息提取能力,而在模型推理时通过结构重参数化将多分支融合为单分支,以降低计算复杂度、加快模型推理速度。然后,利用基于压缩和激励网络的通道注意力机制弥补缺失的通道特征信息,以提高语音识别准确率。最后,在公开数据集Aishell-1上的实验结果表明:相较于Conformer,所提出方法的字错误率降低了10.67%,验证了方法的先进性。此外,RepVGG-SE声学输入网络能够有效提高多种Transformer变体的端到端语音识别模型的整体性能,具有很好的泛化能力。

Monaco计划系统中Conformality函数对宫颈癌容积旋转调强计划的影响

目的 探讨Monaco计划系统中Conformality函数的不同参数值对计划质量的影响。方法 选择15例宫颈癌患者,年龄46~74岁,中位年龄51岁。分别采用Conformality函数参数值为0.25、0.50、0.75、1.00,以及不加函数设计容积旋转调强放射治疗(VMAT)计划,评估靶区及危及器官(OAR)剂量学参数和20 Gy、30 Gy、40 Gy等剂量线的体积和计划执行效率。结果 不同Conformality函数参数值计划的靶区剂量学差异均有统计学意义(P <0.05)。Conformality函数参数值为0.25时,靶区的Dmax、Dmin、Dmean与不加函数的增减幅度分别为2.45%、-0.96%、1.48%,适形度指数(CI)、均匀性指数(HI)增加0.05、0.04。当Conformality函数参数值> 0.50时,CI、HI基本无改变。小肠、结肠、左右股骨头的剂量学差异无统计学意义(P> 0.05)。当Conformality函数参数值为0.25时,直肠的V30、V40[(81.80±7.74)%、(63.44±10.23)%]、膀胱V30、V40[(78.82±5.69)%、(56.40±9.33)%]、正常组织V_(20)、V_(30)、V_(40)的体积[(6 137.64±622.88) cm^(3)、(2 903.55±221.08) cm^(3)、(1 862.93±112.81) cm^(3)]最低。Conformality函数在不同参数之下,膀胱、直肠V_(30)、V_(40)差异均具有统计学意义(P <0.05)。随着Conformality函数参数值增大机器参数值随之减小,机器跳数(MU)、控制点个数(CP)、执行时间(DT)在各Conformality函数参数值之间差异均有统计学意义(P <0.05)。结论 对于宫颈癌在Monaco计划系统中恰当使用Conformality函数设计计划可以提高计划质量,参数值设置在0.25~0.75为宜。综合剂量学参数及计划执行效率,推荐使用0.50。

3D‑Printed Carbon‑Based Conformal Electromagnetic Interference Shielding Module for Integrated Electronics

Electromagnetic interference shielding(EMI SE)modules are the core com-ponent of modern electronics.However,the tra-ditional metal-based SE modules always take up indispensable three-dimensional space inside electronics,posing a major obstacle to the integra-tion of electronics.The innovation of integrating 3D-printed conformal shielding(c-SE)modules with packaging materials onto core electronics offers infinite possibilities to satisfy ideal SE func-tion without occupying additional space.Herein,the 3D printable carbon-based inks with various proportions of graphene and carbon nanotube nanoparticles are well-formulated by manipulating their rheological peculiarity.Accordingly,the free-constructed architectures with arbitrarily-customized structure and multifunctionality are created via 3D printing.In particular,the SE performance of 3D-printed frame is up to 61.4 dB,simultaneously accompanied with an ultralight architecture of 0.076 g cm^(-3) and a superhigh specific shielding of 802.4 dB cm3 g^(-1).Moreover,as a proof-of-concept,the 3D-printed c-SE module is in situ integrated into core electronics,successfully replacing the traditional metal-based module to afford multiple functions for electromagnetic compatibility and thermal dissipa-tion.Thus,this scientific innovation completely makes up the blank for assembling carbon-based c-SE modules and sheds a brilliant light on developing the next generation of high-performance shielding materials with arbitrarily-customized structure for integrated electronics.

Soft,body conformable electronics for thermoregulation enabled by kirigami

The application of thermoelectric devices(TEDs)for personalized thermoregulation is attractive for saving energy while balancing the quality of life.TEDs that directly attach to human skin remarkably minimized the energy wasted for cooling the entire environment.However,facing the extreme dynamic geometry change and strain of human skin,conventional TEDs cannot align with the contour of our bodies for the best thermoregulation effect.Hence,we designed a kirigami-based wearable TED with excellent water vapor permeability,flexibility,and conformability.Numerical analysis and experimental results reveal that our product can withstand various types of large mechanical deformation without circuit rupture.The stated outcome and proposed facile approach not only reinforce the development of wearable TEDs but also offer an innovative opportunity for different electronics that require high conformability.

Gelatin-Based Metamaterial Hydrogel Films with High Conformality for Ultra-Soft Tissue Monitoring

Implantable hydrogel-based bioelectronics(IHB)can precisely monitor human health and diagnose diseases.However,achieving biodegradability,biocompatibility,and high conformality with soft tissues poses significant challenges for IHB.Gelatin is the most suitable candidate for IHB since it is a collagen hydrolysate and a substantial part of the extracellular matrix found naturally in most tissues.This study used 3D printing ultrafine fiber networks with metamaterial design to embed into ultra-low elastic modulus hydrogel to create a novel gelatin-based conductive film(GCF)with mechanical programmability.The regulation of GCF nearly covers soft tissue mechanics,an elastic modulus from 20 to 420 kPa,and a Poisson’s ratio from-0.25 to 0.52.The negative Poisson’s ratio promotes conformality with soft tissues to improve the efficiency of biological interfaces.The GCF can monitor heartbeat signals and respiratory rate by determining cardiac deformation due to its high conformability.Notably,the gelatin characteristics of the biodegradable GCF enable the sensor to monitor and support tissue restoration.The GCF metamaterial design offers a unique idea for bioelectronics to develop implantable sensors that integrate monitoring and tissue repair and a customized method for endowing implanted sensors to be highly conformal with soft tissues.

基于时频感知双路径Conformer的语音增强

近年来,Conformer在语音领域的应用表现较为突出。该模块通过结合多头自注意力机制和卷积神经网络,能够同时关注短时和长时序列信息,从而在语音处理任务中表现出卓越的性能。在此基础上提出了一种基于时频感知双路径Conformer的语音增强网络(TFDPCNet)。首先,该网络将改进的Conformer结构作为核心,采用双路径结构,构成时频感知的双路径Conformer模块(TFDP-Conformer),增强了整体网络的时频提取能力;同时,为了减小时频特征融合的难度,提出了注意力门控交叉融合模块(AGCF),通过额外的注意力门进一步增强了网络训练过程中时频特征的交互,提高了时频特征的利用率;最后,引用度量鉴别器,并对其进行适当剪枝,使得增强后的音频和原始音频在量化评价指标上保持更高的一致性。实验结果表明,相比于TSTNN算法,TFDPCNet在主观和客观指标上都有明显提高。

基于Conformable分数阶导数的灰色Bernoulli模型

为增强灰色Bernoulli模型对各种实际数据序列的适应性,借助分数阶微积分在描述复杂系统中的优势,提出了一种基于Conformable分数阶导数的灰色Bernoulli模型。研究发现,可通过改变结构参数将模型转换为不同的经典灰色预测模型,体现了其统一性。此外,采用粒子群优化算法求解规划模型,获取了模型的最优超参数。最后,用所提模型和5个竞争模型对3个真实案例进行了预测建模,结果表明,所提模型的2项评估指标均优于5个竞争模型,验证了所提模型的有效性和可行性。

Conformal ECO寄存器新增的扫描链自动化接入方案

随着芯片规模的增加,ECO的需求和大小也随之增加,其中当新增寄存器数量达到百位量级时,人工接入扫描链难度也将急剧上升。基于Cadence的Conformal和Innovus等工具,在综合考量逻辑正确性和中后端物理实现可行性的基础上,采用归一思路下的“S”型连线和room值下的再分组等方法,实现了上述问题的自动化和高效化解决,在逻辑上确保了时钟域一致性等问题,物理上同时兼顾了布局布线优化和最大扫描链长度。并且其自动化的高效性,在项目实践中能够快速完成上百数量寄存器的扫描链接入。

Laccase/caffeic acid-catalyzed crosslinking coupled with galactomannan alters the conformational structure of ovalbumin and alleviates Th2-mediated allergic asthma

Ovalbumin(OVA)is the major allergenic protein that can induce T helper 2(Th2)-allergic reactions,for which current treatment options are inadequate.In this study,we developed a polymerized hypoallergenic OVA product via laccase/caffeic acid(Lac/CA)-catalyzed crosslinking in conjunction with galactomannan(Man).The formation of high molecular weight crosslinked polymers and the Ig G-binding were analyzed by sodium dodecyl sulfate-polyacrylamide gel electrophoresis(SDS-PAGE)and Western blotting.The study indicated that Lac/CA-catalyzed crosslinking plus Man conjugation substantially altered secondary and tertiary structures of OVA along with the variation in surface hydrophobicity.Gastrointestinal digestion stability assay indicated that crosslinked OVA exhibited less resistance in simulated gastric fluid(SGF)and simulated intestinal fluid(SIF).Mouse model study indicated that Lac-Man/OVA ameliorated eosinophilic airway inflammatory response and efficiently downregulated the expression of Th2-related cytokines(interleukin(IL)-4,IL-5,and IL-13),and upregulated IFN-γand IL-10 expression.Stimulation of bone marrow-derived dendritic cells with Lac-Man/OVA suppressed the expression of phenotypic maturation markers(CD80 and CD86)and MHC class II molecules,and suppressed the expression levels of proinflammatory cytokines.The knowledge obtained in the present study offers an effective way to acquire a hypoallergenic OVA product that can have a therapeutic effect in alleviating OVA-induced allergic asthma.

Illuminating β-arrestin conformational dynamics by fluorine NMR

In a recent paper, solution-state ^(19)F NMR spectroscopy was used to probe the conformational dynamics of β-arrestin-1, an essential adaptor and signaling component of the G-protein couple receptor (GPCR) signaling pathway. This work reveals a highly complex conformational energy landscape of β-arrestin-1, and illuminates the molecular mechanism of the membrane phosphoinositide PIP2-induced β-arrestin-1 activation at residue level.(https://doi.org/10.1038/s41467-023-43694-1).

Classifying rockburst with confidence:A novel conformal prediction approach

The scientific community recognizes the seriousness of rockbursts and the need for effective mitigation measures.The literature reports various successful applications of machine learning(ML)models for rockburst assessment;however,a significant question remains unanswered:How reliable are these models,and at what confidence level are classifications made?Typically,ML models output single rockburst grade even in the face of intricate and out-of-distribution samples,without any associated confidence value.Given the susceptibility of ML models to errors,it becomes imperative to quantify their uncertainty to prevent consequential failures.To address this issue,we propose a conformal prediction(CP)framework built on traditional ML models(extreme gradient boosting and random forest)to generate valid classifications of rockburst while producing a measure of confidence for its output.The proposed framework guarantees marginal coverage and,in most cases,conditional coverage on the test dataset.The CP was evaluated on a rockburst case in the Sanshandao Gold Mine in China,where it achieved high coverage and efficiency at applicable confidence levels.Significantly,the CP identified several“confident”classifications from the traditional ML model as unreliable,necessitating expert verification for informed decision-making.The proposed framework improves the reliability and accuracy of rockburst assessments,with the potential to bolster user confidence.

Recent advances in protein conformation sampling by combining machine learning with molecular simulation

The rapid advancement and broad application of machine learning(ML)have driven a groundbreaking revolution in computational biology.One of the most cutting-edge and important applications of ML is its integration with molecular simulations to improve the sampling efficiency of the vast conformational space of large biomolecules.This review focuses on recent studies that utilize ML-based techniques in the exploration of protein conformational landscape.We first highlight the recent development of ML-aided enhanced sampling methods,including heuristic algorithms and neural networks that are designed to refine the selection of reaction coordinates for the construction of bias potential,or facilitate the exploration of the unsampled region of the energy landscape.Further,we review the development of autoencoder based methods that combine molecular simulations and deep learning to expand the search for protein conformations.Lastly,we discuss the cutting-edge methodologies for the one-shot generation of protein conformations with precise Boltzmann weights.Collectively,this review demonstrates the promising potential of machine learning in revolutionizing our insight into the complex conformational ensembles of proteins.

Effective approach for conformal subarray design based on maximum entropy of planar mappings

In this paper,an effective algorithm for optimizing the subarray of conformal arrays is proposed.The method first divides theconformal array into several first-level subarrays.It uses the X algorithm to solve the feasible solution of first-level subarray tiling and employs the particle swarm algorithm to optimize the conformal array subarray tiling scheme with the maximum entropy of the planar mapping as the fitness function.Subsequently,convex optimization is applied to optimize the subarray amplitude phase.Data results verify that the method can effectively find the optimal conformal array tiling scheme.

The Relationship between Parental Stress and Child Conformity:The Mediating Role of Resilience

Background:In today’s society,parental stress has become a prevalent and significant issue,impacting not only parents’mental health but also potentially profoundly affecting children’s growth and education.This topic has garnered continuous attention from scholars.The present study aims to delve into the relationship between parental stress and children’s behavior,particularly focusing on children’s conformity and discipline development during crucial stages.This study aims to explore the relationship between parental stress,child conformity,and resilience,and further examines the mediating role of resilience in the relationship between parental stress and child conformity.Methods:We used three scales:the Parental Stress Scale,the Child Conformity Scale,and the Resilience Scale,to survey 890 elementary school students(aged 6–12)and their parents in the Beijing-Tianjin-Hebei region of China.We employed SPSS 26.0 software for data analysis,conducting descriptive statistics,correlation analysis,and mediation effect tests sequentially.In the mediation effect tests,we utilized structural equation modeling(SEM)and regression analysis to examine the mediation effects,ensuring the accuracy and scientific nature of our analysis.Results:Through descriptive statistics,correlation analysis,regression models,and mediation effect tests,we found that parental stress significantly negatively predicts child conformity,while resilience shows a significant positive prediction.Further mediation analysis indicates that resilience plays a partial mediating role between parental stress and child conformity,with the mediation effect accounting for 36.67%.Conclusion:These findings highlight the importance of the family environment on child behavior and provide valuable insights and recommendations for family education practices in the Beijing-Tianjin-Hebei region.Therefore,we suggest future research should further explore the complex relationships among parental stress,child conformity,and resilience,and examine regional differences to better promote children’s overall development.

基于Conformer模型的智能电网调度语音识别研究

完成智能虚拟电网调度,语音识别是重要一部分,识别的准确性直接由语言模型决定。提出一种基于Conformer模型的智能电网调度语音识别技术,在Transformer模型里面引入卷积模块来提高模型的细微特征学习能力,首先介绍了Conformer的原理,并结合LAS解码器构建了语音识别模型;然后输入电网调度语言进行特征提取,提高模型的适应性;最后通过试验验证,所提模型在电网调度语音识别中具有很高的准确性,验证相对于常见的语音识别Transformer模型与CTC模型,在验证集上的字错率分别降低了11.23%、21.76%,表明模型具有很好的效果。

基于Conformer的实时多场景说话人识别模型

为解决在多场景(跨域、长时以及噪声干扰语音场景)下说话人确认系统性能较差的问题,提出了一种基于Conformer构建的、实时多场景鲁棒的说话人识别模型——PMS-Conformer。PMS-Conformer的设计灵感来自于先进的模型MFA-Conformer。PMS-Conformer对MFA-Conformer的声学特征提取器、网络组件和损失函数计算模块进行了改进,其具有新颖有效的声学特征提取器,以及鲁棒的、具有较强泛化能力的声纹嵌入码提取器。基于VoxCeleb1&2数据集实现了PMS-Conformer的训练;开展了PMS-Conformer与基线MFA-Conformer以及ECAPA-TDNN在说话人确认任务上的性能对比评估实验。实验结果表明在长语音SITW、跨域VoxMovies以及加噪处理的VoxCeleb-O测试集上,以PMS-Conformer构建的说话人确认系统的性能比用这两个基线构建的说话人确认系统更有竞争力;并且在声纹嵌入码提取器的可训练参数(Params)和推理速度(RTF)方面,PMS-Conformer明显优于ECAPA-TDNN。实验结果说明了PMS-Conformer在实时多场景下具有良好的性能。

Thin-Shell Wormholes Admitting Conformal Motions in Spacetimes of Embedding Class One

This paper discusses the feasibility of thin-shell wormholes in spacetimes of embedding class one admitting a one-parameter group of conformal motions. It is shown that the surface energy density σis positive, while the surface pressure is negative, resulting in , thereby signaling a violation of the null energy condition, a necessary condition for holding a wormhole open. For a Morris-Thorne wormhole, matter that violates the null energy condition is referred to as “exotic”. For the thin-shell wormholes in this paper, however, the violation has a physical explanation since it is a direct consequence of the embedding theory in conjunction with the assumption of conformal symmetry. These properties avoid the need to hypothesize the existence of the highly problematical exotic matter.

Momentum as Translations at Conformal Infinity

Although General Relativity is the classic example of a physical theory based on differential geometry, the momentum tensor is the only part of the field equation that is not derived from or interpreted with differential geometry. This work extends General Relativity and Einstein-Cartan theory by augmenting the Poincaré group with projective (special) conformal transformations, which are translations at conformal infinity. Momentum becomes a part of the differential geometry of spacetime. The Lie algebra of these transformations is represented by vectorfields on an associated Minkowski fiber space. Variation of projective conformal scalar curvature generates a 2-index tensor that serves as linear momentum in the field equations of General Relativity. The computation yields a constructive realization of Mach’s principle: local inertia is determined by local motion relative to mass at conformal infinity in each fiber. The vectorfields have a cellular structure that is similar to that of turbulent fluids.