首页 > 最新文献

Speech Communication最新文献

英文 中文
Robust voice activity detection using an auditory-inspired masked modulation encoder based convolutional attention network 使用基于卷积注意力网络的听觉启发式掩蔽调制编码器进行鲁棒语音活动检测
IF 3.2 3区 计算机科学 Q2 ACOUSTICS Pub Date : 2023-12-14 DOI: 10.1016/j.specom.2023.103024
Nan Li , Longbiao Wang , Meng Ge , Masashi Unoki , Sheng Li , Jianwu Dang

Deep learning has revolutionized voice activity detection (VAD) by offering promising solutions. However, directly applying traditional features, such as raw waveforms and Mel-frequency cepstral coefficients, to deep neural networks often leads to degraded VAD performance due to noise interference. In contrast, humans possess the remarkable ability to discern speech in complex and noisy environments, which motivated us to draw inspiration from the human auditory system. We propose a robust VAD algorithm called auditory-inspired masked modulation encoder based convolutional attention network (AMME-CANet) that integrates our AMME with CANet. Firstly, we investigate the design of auditory-inspired modulation features as a deep-learning encoder (AME), effectively simulating the process of sound-signal transmission to inner ear hair cells and subsequent modulation filtering by neural cells. Secondly, building upon the observed masking effects in the human auditory system, we enhance our auditory-inspired modulation encoder by incorporating a masking mechanism resulting in the AMME. The AMME amplifies cleaner speech frequencies while suppressing noise components. Thirdly, inspired by the human auditory mechanism and capitalizing on contextual information, we leverage the attention mechanism for VAD. This methodology uses an attention mechanism to assign higher weights to contextual information containing richer and more informative cues. Through extensive experimentation and evaluation, we demonstrated the superior performance of AMME-CANet in enhancing VAD under challenging noise conditions.

深度学习为语音活动检测(VAD)带来了革命性的变化,提供了前景广阔的解决方案。然而,将原始波形和梅尔频率共振频率系数等传统特征直接应用于深度神经网络,往往会因噪声干扰而导致 VAD 性能下降。相比之下,人类拥有在复杂和嘈杂环境中辨别语音的非凡能力,这促使我们从人类听觉系统中汲取灵感。我们提出了一种稳健的 VAD 算法,称为基于听觉启发的掩蔽调制编码器卷积注意网络(AMME-CANet),它将我们的 AMME 与 CANet 集成在一起。首先,我们研究了作为深度学习编码器(AME)的听觉启发调制特征的设计,有效地模拟了声音信号传输到内耳毛细胞以及神经细胞随后进行调制过滤的过程。其次,基于在人类听觉系统中观察到的掩蔽效应,我们通过在 AMME 中加入掩蔽机制来增强我们的听觉启发调制编码器。AMME 可放大较纯净的语音频率,同时抑制噪声成分。第三,受人类听觉机制的启发并利用上下文信息,我们利用注意力机制进行 VAD。这种方法利用注意力机制,为包含更丰富、更翔实线索的上下文信息分配更高的权重。通过广泛的实验和评估,我们证明了 AMME-CANet 在具有挑战性的噪声条件下增强 VAD 的卓越性能。
{"title":"Robust voice activity detection using an auditory-inspired masked modulation encoder based convolutional attention network","authors":"Nan Li ,&nbsp;Longbiao Wang ,&nbsp;Meng Ge ,&nbsp;Masashi Unoki ,&nbsp;Sheng Li ,&nbsp;Jianwu Dang","doi":"10.1016/j.specom.2023.103024","DOIUrl":"10.1016/j.specom.2023.103024","url":null,"abstract":"<div><p><span><span>Deep learning<span> has revolutionized voice activity detection (VAD) by offering promising solutions. However, directly applying traditional features, such as raw waveforms and Mel-frequency </span></span>cepstral coefficients, to deep </span>neural networks<span><span> often leads to degraded VAD performance due to noise interference. In contrast, humans possess the remarkable ability to discern speech in complex and noisy environments, which motivated us to draw inspiration from the human auditory system. We propose a robust VAD algorithm called auditory-inspired masked modulation encoder based convolutional </span>attention network<span> (AMME-CANet) that integrates our AMME with CANet. Firstly, we investigate the design of auditory-inspired modulation features as a deep-learning encoder (AME), effectively simulating the process of sound-signal transmission to inner ear hair cells and subsequent modulation filtering by neural cells. Secondly, building upon the observed masking effects in the human auditory system, we enhance our auditory-inspired modulation encoder by incorporating a masking mechanism resulting in the AMME. The AMME amplifies cleaner speech frequencies while suppressing noise components. Thirdly, inspired by the human auditory mechanism and capitalizing on contextual information, we leverage the attention mechanism for VAD. This methodology uses an attention mechanism to assign higher weights to contextual information containing richer and more informative cues. Through extensive experimentation and evaluation, we demonstrated the superior performance of AMME-CANet in enhancing VAD under challenging noise conditions.</span></span></p></div>","PeriodicalId":49485,"journal":{"name":"Speech Communication","volume":"157 ","pages":"Article 103024"},"PeriodicalIF":3.2,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138714391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Performance of single-channel speech enhancement algorithms on Mandarin listeners with different immersion conditions in New Zealand English 单通道语音增强算法在新西兰英语中不同浸入条件下普通话听者身上的表现
IF 3.2 3区 计算机科学 Q2 ACOUSTICS Pub Date : 2023-12-14 DOI: 10.1016/j.specom.2023.103026
Yunqi C. Zhang , Yusuke Hioka , C.T. Justine Hui , Catherine I. Watson

Speech enhancement (SE) is a widely used technology to improve the quality and intelligibility of noisy speech. So far, SE algorithms were designed and evaluated on native listeners only, but not on non-native listeners who are known to be more disadvantaged when listening in noisy environments. This paper investigates the performance of five widely used single-channel SE algorithms on early-immersed New Zealand English (NZE) listeners and native Mandarin listeners with different immersion conditions in NZE under negative input signal-to-noise ratio (SNR) by conducting a subjective listening test in NZE sentences. The performance of the SE algorithms in terms of speech intelligibility in the three participant groups was investigated. The result showed that the early-immersed group always achieved the highest intelligibility. The late-immersed group outperformed the non-immersed group for higher input SNR conditions, possibly due to the increasing familiarity with the NZE accent, whereas this advantage disappeared at the lowest tested input SNR conditions. The SE algorithms tested in this study failed to improve and rather degraded the speech intelligibility, indicating that these SE algorithms may not be able to reduce the perception gap between early-, late- and non-immersed listeners, nor able to improve the speech intelligibility under negative input SNR in general. These findings have implications for the future development of SE algorithms tailored to Mandarin listeners, and for understanding the impact of language immersion on speech perception in noise.

语音增强(SE)是一种广泛应用的技术,用于提高嘈杂语音的质量和可懂度。迄今为止,SE 算法的设计和评估对象都是母语听众,而非母语听众在嘈杂环境中的听力状况则更为不利。本文通过在新西兰英语句子中进行主观听力测试,研究了五种广泛使用的单通道 SE 算法在不同输入信噪比(SNR)条件下对早期浸入新西兰英语(NZE)的听者和母语普通话听者的性能表现。研究了 SE 算法在三组听者中的语音清晰度表现。结果表明,早熟组的语音清晰度总是最高的。在较高的输入信噪比条件下,晚期浸入组的表现优于非浸入组,这可能是由于对新西兰英语口音的熟悉程度不断提高,而在测试的最低输入信噪比条件下,这种优势消失了。本研究中测试的 SE 算法未能改善语音可懂度,反而降低了语音可懂度,这表明这些 SE 算法可能无法缩小早期、晚期和非浸入型听者之间的感知差距,也无法改善负输入信噪比条件下的语音可懂度。这些发现对未来开发适合普通话听者的 SE 算法,以及理解语言浸入对噪声中语音感知的影响具有重要意义。
{"title":"Performance of single-channel speech enhancement algorithms on Mandarin listeners with different immersion conditions in New Zealand English","authors":"Yunqi C. Zhang ,&nbsp;Yusuke Hioka ,&nbsp;C.T. Justine Hui ,&nbsp;Catherine I. Watson","doi":"10.1016/j.specom.2023.103026","DOIUrl":"10.1016/j.specom.2023.103026","url":null,"abstract":"<div><p>Speech enhancement (SE) is a widely used technology to improve the quality and intelligibility of noisy speech. So far, SE algorithms were designed and evaluated on native listeners only, but not on non-native listeners who are known to be more disadvantaged when listening in noisy environments. This paper investigates the performance of five widely used single-channel SE algorithms on early-immersed New Zealand English (NZE) listeners and native Mandarin listeners with different immersion conditions in NZE under negative input signal-to-noise ratio (SNR) by conducting a subjective listening test in NZE sentences. The performance of the SE algorithms in terms of speech intelligibility in the three participant groups was investigated. The result showed that the early-immersed group always achieved the highest intelligibility. The late-immersed group outperformed the non-immersed group for higher input SNR conditions, possibly due to the increasing familiarity with the NZE accent, whereas this advantage disappeared at the lowest tested input SNR conditions. The SE algorithms tested in this study failed to improve and rather degraded the speech intelligibility, indicating that these SE algorithms may not be able to reduce the perception gap between early-, late- and non-immersed listeners, nor able to improve the speech intelligibility under negative input SNR in general. These findings have implications for the future development of SE algorithms tailored to Mandarin listeners, and for understanding the impact of language immersion on speech perception in noise.</p></div>","PeriodicalId":49485,"journal":{"name":"Speech Communication","volume":"157 ","pages":"Article 103026"},"PeriodicalIF":3.2,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0167639323001607/pdfft?md5=34c5bfa551c84f84c20ac950e89b00d4&pid=1-s2.0-S0167639323001607-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138681095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Back to grammar: Using grammatical error correction to automatically assess L2 speaking proficiency 回到语法:利用语法纠错自动评估 L2 口语水平
IF 3.2 3区 计算机科学 Q2 ACOUSTICS Pub Date : 2023-12-12 DOI: 10.1016/j.specom.2023.103025
Stefano Bannò , Marco Matassoni

In an interconnected world where English has become the lingua franca of culture, entertainment, business, and academia, the growing demand for learning English as a second language (L2) has led to an increasing interest in automatic approaches for assessing spoken language proficiency. In this regard, mastering grammar is one of the key elements of L2 proficiency.

In this paper, we illustrate an approach to L2 proficiency assessment and feedback based on grammatical features using only publicly available data for training and a small proprietary dataset for testing. Specifically, we implement it in a cascaded fashion, starting from learners’ utterances, investigating disfluency detection, exploring spoken grammatical error correction (GEC), and finally using grammatical features extracted with the spoken GEC module for proficiency assessment.

We compare this grading system to a BERT-based grader and find that the two systems have similar performances when using manual transcriptions, but their combinations bring significant improvements to the assessment performance and enhance validity and explainability. Instead, when using automatic transcriptions, the GEC-based grader obtains better results than the BERT-based grader.

The results obtained are discussed and evaluated with appropriate metrics across the proposed pipeline.

在一个相互联系的世界里,英语已成为文化、娱乐、商业和学术界的通用语言,人们对英语作为第二语言(L2)的学习需求日益增长,这导致人们对口语能力自动评估方法的兴趣与日俱增。在本文中,我们展示了一种基于语法特征的 L2 能力评估和反馈方法,该方法仅使用公开数据进行训练,并使用一个小型专有数据集进行测试。具体来说,我们以级联的方式实施这种方法,从学习者的语篇开始,研究不流畅检测,探索口语语法错误纠正(GEC),最后使用口语语法错误纠正模块提取的语法特征进行能力评估。我们将这种评分系统与基于 BERT 的评分系统进行了比较,发现这两种系统在使用人工转录时具有相似的性能,但它们的组合能显著提高评估性能,并增强有效性和可解释性。相反,在使用自动转录时,基于 GEC 的评分器比基于 BERT 的评分器获得了更好的结果。
{"title":"Back to grammar: Using grammatical error correction to automatically assess L2 speaking proficiency","authors":"Stefano Bannò ,&nbsp;Marco Matassoni","doi":"10.1016/j.specom.2023.103025","DOIUrl":"10.1016/j.specom.2023.103025","url":null,"abstract":"<div><p>In an interconnected world where English has become the lingua franca of culture, entertainment, business, and academia, the growing demand for learning English as a second language (L2) has led to an increasing interest in automatic approaches for assessing spoken language proficiency. In this regard, mastering grammar is one of the key elements of L2 proficiency.</p><p>In this paper, we illustrate an approach to L2 proficiency assessment and feedback based on grammatical features using only publicly available data for training and a small proprietary dataset for testing. Specifically, we implement it in a cascaded fashion, starting from learners’ utterances, investigating disfluency detection, exploring spoken grammatical error correction (GEC), and finally using grammatical features extracted with the spoken GEC module for proficiency assessment.</p><p>We compare this grading system to a BERT-based grader and find that the two systems have similar performances when using manual transcriptions, but their combinations bring significant improvements to the assessment performance and enhance validity and explainability. Instead, when using automatic transcriptions, the GEC-based grader obtains better results than the BERT-based grader.</p><p>The results obtained are discussed and evaluated with appropriate metrics across the proposed pipeline.</p></div>","PeriodicalId":49485,"journal":{"name":"Speech Communication","volume":"157 ","pages":"Article 103025"},"PeriodicalIF":3.2,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138580415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Speakers’ vocal expression of sexual orientation depends on experimenter gender 说话者对性取向的声音表达取决于实验者的性别
IF 3.2 3区 计算机科学 Q2 ACOUSTICS Pub Date : 2023-12-04 DOI: 10.1016/j.specom.2023.103023
Sven Kachel , Adrian P. Simpson , Melanie C. Steffens

Since the early days of (phonetic) convergence research, one of the main questions is which individuals are more likely to adapt their speech to others. Especially differences between women and men have been researched with a high intensity. Using a differential approach as well, we complement the existing literature by focusing on another gender-related characteristic, namely sexual orientation. The present study aims to investigate whether and how women differing in sexual orientation vary in their speaking behavior, especially mean fundamental frequency (f0), in the presence of a female vs. male experimenter. Lesbian (n = 19) and straight female speakers (n = 18) engaged in two interactions each: First, they either engaged with a female or male experimenter, and second with the other-gender experimenter (counter-balanced and random assignment to conditions). For each interaction, recordings of read and spontaneous speech were collected. Analyses of read speech demonstrated mirroring of the first experimenter’s mean f0 which persisted even in the presence of the second experimenter. In spontaneous speech, this order effect interacted with exclusiveness of sexual orientation: Mirroring was found for participants who reported being exclusively lesbian/straight, not for those who reported being mainly lesbian/straight. We discuss implications for studies on convergence and research practice in general.

自(语音)趋同研究的早期以来,主要问题之一是哪个个体更有可能使自己的语言适应他人。尤其是女性和男性之间的差异已经得到了高强度的研究。我们也使用了一种不同的方法,通过关注另一个与性别相关的特征,即性取向,来补充现有的文献。本研究旨在调查不同性取向的女性在男女实验者在场的情况下,她们的说话行为,尤其是平均基本频率(0)是否以及如何发生变化。女同性恋者(n = 19)和异性恋女性演讲者(n = 18)各自进行了两次互动:第一次,她们与女性或男性实验者互动,第二次与异性实验者互动(平衡和随机分配条件)。对于每次互动,收集阅读和自发语音的录音。对读语音的分析表明,即使在第二个实验者在场的情况下,平均0对第一个实验者的适应仍然存在。在自发演讲中,这种顺序效应与性取向的排他性相互作用:在那些报告自己完全是女同性恋/异性恋的参与者中发现了适应,而在那些报告自己主要是女同性恋/异性恋的参与者中没有发现适应。我们讨论了一般意义上的收敛研究和研究实践的含义。
{"title":"Speakers’ vocal expression of sexual orientation depends on experimenter gender","authors":"Sven Kachel ,&nbsp;Adrian P. Simpson ,&nbsp;Melanie C. Steffens","doi":"10.1016/j.specom.2023.103023","DOIUrl":"10.1016/j.specom.2023.103023","url":null,"abstract":"<div><p>Since the early days of (phonetic) convergence research, one of the main questions is which individuals are more likely to adapt their speech to others. Especially differences between women and men have been researched with a high intensity. Using a differential approach as well, we complement the existing literature by focusing on another gender-related characteristic, namely sexual orientation. The present study aims to investigate whether and how women differing in sexual orientation vary in their speaking behavior, especially mean fundamental frequency (f0), in the presence of a female vs. male experimenter. Lesbian (<em>n</em> = 19) and straight female speakers (<em>n</em> = 18) engaged in two interactions each: First, they either engaged with a female or male experimenter, and second with the other-gender experimenter (counter-balanced and random assignment to conditions). For each interaction, recordings of read and spontaneous speech were collected. Analyses of read speech demonstrated mirroring of the first experimenter’s mean f0 which persisted even in the presence of the second experimenter. In spontaneous speech, this order effect interacted with exclusiveness of sexual orientation: Mirroring was found for participants who reported being exclusively lesbian/straight, not for those who reported being mainly lesbian/straight. We discuss implications for studies on convergence and research practice in general.</p></div>","PeriodicalId":49485,"journal":{"name":"Speech Communication","volume":"156 ","pages":"Article 103023"},"PeriodicalIF":3.2,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0167639323001577/pdfft?md5=e1280cda33f537c756c6ad3e4b34309d&pid=1-s2.0-S0167639323001577-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138542558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Choosing only the best voice imitators: Top-K many-to-many voice conversion with StarGAN 只选择最好的语音模仿者:Top-K多对多语音转换与StarGAN
IF 3.2 3区 计算机科学 Q2 ACOUSTICS Pub Date : 2023-11-30 DOI: 10.1016/j.specom.2023.103022
Claudio Fernandez-Martín , Adrian Colomer , Claudio Panariello , Valery Naranjo

Voice conversion systems have become increasingly important as the use of voice technology grows. Deep learning techniques, specifically generative adversarial networks (GANs), have enabled significant progress in the creation of synthetic media, including the field of speech synthesis. One of the most recent examples, StarGAN-VC, uses a single pair of generator and discriminator to convert voices between multiple speakers. However, the training stability of GANs can be an issue. The Top-K methodology, which trains the generator using only the best K generated samples that “fool” the discriminator, has been applied to image tasks and simple GAN architectures. In this work, we demonstrate that the Top-K methodology can improve the quality and stability of converted voices in a state-of-the-art voice conversion system like StarGAN-VC. We also explore the optimal time to implement the Top-K methodology and how to reduce the value of K during training. Through both quantitative and qualitative studies, it was found that the Top-K methodology leads to quicker convergence and better conversion quality compared to regular or vanilla training. In addition, human listeners perceived the samples generated using Top-K as more natural and were more likely to believe that they were produced by a human speaker. The results of this study demonstrate that the Top-K methodology can effectively improve the performance of deep learning-based voice conversion systems.

随着语音技术应用的增长,语音转换系统变得越来越重要。深度学习技术,特别是生成对抗网络(GANs),使合成媒体的创造取得了重大进展,包括语音合成领域。最近的一个例子是StarGAN-VC,它使用一对发生器和鉴别器来转换多个扬声器之间的声音。然而,gan的训练稳定性可能是一个问题。Top-K方法只使用最好的K个生成样本来训练生成器,这些样本可以“欺骗”鉴别器,该方法已应用于图像任务和简单的GAN架构。在这项工作中,我们证明了Top-K方法可以在最先进的语音转换系统(如StarGAN-VC)中提高转换语音的质量和稳定性。我们还探讨了实现Top-K方法的最佳时间以及如何在训练期间减少K的值。通过定量和定性研究,发现Top-K方法与常规或香草训练相比,收敛速度更快,转换质量更好。此外,人类听众认为使用Top-K生成的样本更自然,更有可能相信它们是由人类说话者产生的。本研究的结果表明,Top-K方法可以有效地提高基于深度学习的语音转换系统的性能。
{"title":"Choosing only the best voice imitators: Top-K many-to-many voice conversion with StarGAN","authors":"Claudio Fernandez-Martín ,&nbsp;Adrian Colomer ,&nbsp;Claudio Panariello ,&nbsp;Valery Naranjo","doi":"10.1016/j.specom.2023.103022","DOIUrl":"https://doi.org/10.1016/j.specom.2023.103022","url":null,"abstract":"<div><p>Voice conversion systems have become increasingly important as the use of voice technology grows. Deep learning techniques, specifically generative adversarial networks (GANs), have enabled significant progress in the creation of synthetic media, including the field of speech synthesis. One of the most recent examples, StarGAN-VC, uses a single pair of generator and discriminator to convert voices between multiple speakers. However, the training stability of GANs can be an issue. The Top-K methodology, which trains the generator using only the best <span><math><mi>K</mi></math></span> generated samples that “fool” the discriminator, has been applied to image tasks and simple GAN architectures. In this work, we demonstrate that the Top-K methodology can improve the quality and stability of converted voices in a state-of-the-art voice conversion system like StarGAN-VC. We also explore the optimal time to implement the Top-K methodology and how to reduce the value of <span><math><mi>K</mi></math></span> during training. Through both quantitative and qualitative studies, it was found that the Top-K methodology leads to quicker convergence and better conversion quality compared to regular or vanilla training. In addition, human listeners perceived the samples generated using Top-K as more natural and were more likely to believe that they were produced by a human speaker. The results of this study demonstrate that the Top-K methodology can effectively improve the performance of deep learning-based voice conversion systems.</p></div>","PeriodicalId":49485,"journal":{"name":"Speech Communication","volume":"156 ","pages":"Article 103022"},"PeriodicalIF":3.2,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0167639323001565/pdfft?md5=74a68a8324a3af4dc4558e4166e99f23&pid=1-s2.0-S0167639323001565-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138474840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multiscale-multichannel feature extraction and classification through one-dimensional convolutional neural network for Speech emotion recognition 基于一维卷积神经网络的语音情感识别多尺度多通道特征提取与分类
IF 3.2 3区 计算机科学 Q2 ACOUSTICS Pub Date : 2023-11-22 DOI: 10.1016/j.specom.2023.103010
Minying Liu , Alex Noel Joseph Raj , Vijayarajan Rajangam , Kunwu Ma , Zhemin Zhuang , Shuxin Zhuang

Speech emotion recognition (SER) is a crucial field of research in artificial intelligence and human–computer interaction. Extracting effective speech features for emotion recognition is a continuing research focus in SER. Most research has focused on finding an optimal speech feature to extract hidden local features while ignoring the global relationships of the speech signal. In this paper, we propose a method that utilizes a multiscale-multichannel feature extraction structure with global and local information to obtain comprehensive speech features. Our approach employs a one-dimensional convolutional neural network (1D CNN) for feature learning and emotion recognition, capturing both spectral and spatial characteristics of speech for superior learning capabilities with improved SER results. We conducted extensive experiments on publicly available emotion recognition datasets, employing three distinct data augmentation (DA) techniques to enhance model generalization. Our model utilized Mel-frequency cepstral coefficients and zero-crossing rate features from speech samples for training and outperformed state-of-the-art techniques in terms of accuracy. Additionally, we conducted experiments to validate the effectiveness and reliability of our proposed method.

语音情感识别(SER)是人工智能和人机交互领域的一个重要研究领域。提取有效的语音特征用于情感识别一直是语音识别领域的研究热点。大多数研究都集中在寻找最优的语音特征来提取隐藏的局部特征,而忽略了语音信号的全局关系。在本文中,我们提出了一种利用全局和局部信息的多尺度多通道特征提取结构来获得综合语音特征的方法。我们的方法采用一维卷积神经网络(1D CNN)进行特征学习和情感识别,捕获语音的频谱和空间特征,从而获得更好的学习能力和改进的SER结果。我们在公开可用的情绪识别数据集上进行了广泛的实验,采用三种不同的数据增强(DA)技术来增强模型泛化。我们的模型利用mel频率倒谱系数和语音样本的过零率特征进行训练,在准确性方面优于最先进的技术。此外,我们还进行了实验来验证我们提出的方法的有效性和可靠性。
{"title":"Multiscale-multichannel feature extraction and classification through one-dimensional convolutional neural network for Speech emotion recognition","authors":"Minying Liu ,&nbsp;Alex Noel Joseph Raj ,&nbsp;Vijayarajan Rajangam ,&nbsp;Kunwu Ma ,&nbsp;Zhemin Zhuang ,&nbsp;Shuxin Zhuang","doi":"10.1016/j.specom.2023.103010","DOIUrl":"https://doi.org/10.1016/j.specom.2023.103010","url":null,"abstract":"<div><p>Speech emotion recognition (SER) is a crucial field of research in artificial intelligence and human–computer interaction. Extracting effective speech features for emotion recognition is a continuing research focus in SER. Most research has focused on finding an optimal speech feature to extract hidden local features while ignoring the global relationships of the speech signal. In this paper, we propose a method that utilizes a multiscale-multichannel feature extraction structure with global and local information to obtain comprehensive speech features. Our approach employs a one-dimensional convolutional neural network (1D CNN) for feature learning and emotion recognition, capturing both spectral and spatial characteristics of speech for superior learning capabilities with improved SER results. We conducted extensive experiments on publicly available emotion recognition datasets, employing three distinct data augmentation (DA) techniques to enhance model generalization. Our model utilized Mel-frequency cepstral coefficients and zero-crossing rate features from speech samples for training and outperformed state-of-the-art techniques in terms of accuracy. Additionally, we conducted experiments to validate the effectiveness and reliability of our proposed method.</p></div>","PeriodicalId":49485,"journal":{"name":"Speech Communication","volume":"156 ","pages":"Article 103010"},"PeriodicalIF":3.2,"publicationDate":"2023-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0167639323001449/pdfft?md5=a1739967e793340202a345ded16beeca&pid=1-s2.0-S0167639323001449-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138430705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Selective transfer subspace learning for small-footprint end-to-end cross-domain keyword spotting 小空间端到端跨域关键字识别的选择性迁移子空间学习
IF 3.2 3区 计算机科学 Q2 ACOUSTICS Pub Date : 2023-11-22 DOI: 10.1016/j.specom.2023.103019
Fei Ma, Chengliang Wang, Xusheng Li, Zhuo Zeng

In small-footprint end-to-end keyword spotting, it is often expensive and time-consuming to acquire sufficient labels in various speech scenarios. To overcome this problem, transfer learning leverages the rich knowledge of the auxiliary domain to annotate the unlabeled target data. However, most existing transfer learning methods typically learn a domain-invariant feature representation while ignoring the negative transfer problem. In this paper, we propose a new and general cross-domain keyword spotting framework called selective transfer subspace learning (STSL) that avoid negative transfer and dramatically improve the accuracy for cross-domain keyword spotting by actively selecting appropriate source samples. Specifically, STSL first aligns geometrical relationship and weighted distribution discrepancy to learn a domain-invariant projection subspace. Then, it actively selects appropriate source samples that are similar to the target domain for transfer learning to avoid negative transfer. Finally, we formulate a minimization problem that alternately optimizes the projection subspace and source active selection, giving an effective optimization. Experimental results on 10 groups of cross-domain keyword spotting tasks show that our STSL outperforms some state-of-the-art transfer learning methods and no transfer learning methods.

在小占用空间的端到端关键字识别中,在各种语音场景中获取足够的标签通常既昂贵又耗时。为了克服这一问题,迁移学习利用辅助领域的丰富知识对未标记的目标数据进行标注。然而,大多数现有的迁移学习方法通常只学习域不变的特征表示,而忽略了负迁移问题。本文提出了一种新的通用跨域关键字识别框架——选择性迁移子空间学习(STSL),该框架通过主动选择合适的源样本,避免了负迁移,显著提高了跨域关键字识别的准确性。具体而言,STSL首先对几何关系和加权分布差异进行对齐,学习域不变投影子空间。然后,主动选择与目标域相似的合适源样本进行迁移学习,避免负迁移。最后,我们提出了一个最小化问题,交替优化投影子空间和源主动选择,给出了一个有效的优化。在10组跨域关键字识别任务上的实验结果表明,我们的STSL算法优于一些最先进的迁移学习方法和无迁移学习方法。
{"title":"Selective transfer subspace learning for small-footprint end-to-end cross-domain keyword spotting","authors":"Fei Ma,&nbsp;Chengliang Wang,&nbsp;Xusheng Li,&nbsp;Zhuo Zeng","doi":"10.1016/j.specom.2023.103019","DOIUrl":"https://doi.org/10.1016/j.specom.2023.103019","url":null,"abstract":"<div><p>In small-footprint end-to-end keyword spotting, it is often expensive and time-consuming to acquire sufficient labels in various speech scenarios. To overcome this problem, transfer learning leverages the rich knowledge of the auxiliary domain to annotate the unlabeled target data. However, most existing transfer learning methods typically learn a domain-invariant feature representation while ignoring the negative transfer problem. In this paper, we propose a new and general cross-domain keyword spotting framework called selective transfer subspace learning (STSL) that avoid negative transfer and dramatically improve the accuracy for cross-domain keyword spotting by actively selecting appropriate source samples. Specifically, STSL first aligns geometrical relationship and weighted distribution discrepancy to learn a domain-invariant projection subspace. Then, it actively selects appropriate source samples that are similar to the target domain for transfer learning to avoid negative transfer. Finally, we formulate a minimization problem that alternately optimizes the projection subspace and source active selection, giving an effective optimization. Experimental results on 10 groups of cross-domain keyword spotting tasks show that our STSL outperforms some state-of-the-art transfer learning methods and no transfer learning methods.</p></div>","PeriodicalId":49485,"journal":{"name":"Speech Communication","volume":"156 ","pages":"Article 103019"},"PeriodicalIF":3.2,"publicationDate":"2023-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S016763932300153X/pdfft?md5=82a39d003305603c8c276ad8a7d9c674&pid=1-s2.0-S016763932300153X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138448358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An introduction to pluricentric languages in speech science and technology 语音科学与技术中的多中心语言导论
IF 3.2 3区 计算机科学 Q2 ACOUSTICS Pub Date : 2023-11-21 DOI: 10.1016/j.specom.2023.103007
Barbara Schuppler , Martine Adda-Decker , Catia Cucchiarini , Rudolf Muhr

Pluricentric languages are languages that are spoken in at least two countries where they have an official function and thus develop national varieties with specific linguistic and pragmatic features. Presently 43 languages have been identified as belonging to this category, for instance, English, Spanish, German, Bengali, Hindi and Urdu. This article forms an introduction to the special issue “Pluricentric Languages in Speech Science and Technology” by giving an overview of current challenges with respect to the development of speech and language resources, annotation and analysis tools, as well as speech technology services for pluricentric languages. The article discusses potential solutions that come from cross-fertilization: on the one hand, how phonetic and linguistic knowledge may contribute to advancements in speech technology, and on the other, how speech technology may facilitate phonetic and linguistic studies on pluricentric languages. In our discussion, we include the research methods and findings of the eight research articles of this special issue and point towards promising paths for future research in the field.

多中心语言是至少在两个国家使用的语言,在那里它们具有官方功能,从而发展出具有特定语言和语用特征的民族变体。目前已确定有43种语言属于这一类,例如英语、西班牙语、德语、孟加拉语、印地语和乌尔都语。本文对“语音科学与技术中的多中心语言”特刊进行了介绍,概述了当前多中心语言在语音和语言资源开发、注释和分析工具以及语音技术服务等方面面临的挑战。本文讨论了来自交叉受精的潜在解决方案:一方面,语音和语言知识如何促进语音技术的进步,另一方面,语音技术如何促进多中心语言的语音和语言研究。在我们的讨论中,我们包括了这期特刊的八篇研究文章的研究方法和发现,并指出了该领域未来研究的有希望的路径。
{"title":"An introduction to pluricentric languages in speech science and technology","authors":"Barbara Schuppler ,&nbsp;Martine Adda-Decker ,&nbsp;Catia Cucchiarini ,&nbsp;Rudolf Muhr","doi":"10.1016/j.specom.2023.103007","DOIUrl":"https://doi.org/10.1016/j.specom.2023.103007","url":null,"abstract":"<div><p>Pluricentric languages are languages that are spoken in at least two countries where they have an official function and thus develop national varieties with specific linguistic and pragmatic features. Presently 43 languages have been identified as belonging to this category, for instance, English, Spanish, German, Bengali, Hindi and Urdu. This article forms an introduction to the special issue “Pluricentric Languages in Speech Science and Technology” by giving an overview of current challenges with respect to the development of speech and language resources, annotation and analysis tools, as well as speech technology services for pluricentric languages. The article discusses potential solutions that come from cross-fertilization: on the one hand, how phonetic and linguistic knowledge may contribute to advancements in speech technology, and on the other, how speech technology may facilitate phonetic and linguistic studies on pluricentric languages. In our discussion, we include the research methods and findings of the eight research articles of this special issue and point towards promising paths for future research in the field.</p></div>","PeriodicalId":49485,"journal":{"name":"Speech Communication","volume":"156 ","pages":"Article 103007"},"PeriodicalIF":3.2,"publicationDate":"2023-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0167639323001413/pdfft?md5=6872041b83bb49295950af0392609d75&pid=1-s2.0-S0167639323001413-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138397354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Compact deep neural networks for real-time speech enhancement on resource-limited devices 用于资源有限设备上实时语音增强的紧凑深度神经网络
IF 3.2 3区 计算机科学 Q2 ACOUSTICS Pub Date : 2023-11-19 DOI: 10.1016/j.specom.2023.103008
Fazal E Wahab , Zhongfu Ye , Nasir Saleem , Rizwan Ullah

In real-time applications, the aim of speech enhancement (SE) is to achieve optimal performance while ensuring computational efficiency and near-instant outputs. Many deep neural models have achieved optimal performance in terms of speech quality and intelligibility. However, formulating efficient and compact deep neural models for real-time processing on resource-limited devices remains a challenge. This study presents a compact neural model designed in a complex frequency domain for speech enhancement, optimized for resource-limited devices. The proposed model combines convolutional encoder–decoder and recurrent architectures to effectively learn complex mappings from noisy speech for real-time speech enhancement, enabling low-latency causal processing. Recurrent architectures such as Long-Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and Simple Recurrent Unit (SRU), are incorporated as bottlenecks to capture temporal dependencies and improve the performance of SE. By representing the speech in the complex frequency domain, the proposed model processes both magnitude and phase information. Further, this study extends the proposed models and incorporates attention-gate-based skip connections, enabling the models to focus on relevant information and dynamically weigh the important features. The results show that the proposed models outperform the recent benchmark models and obtain better speech quality and intelligibility. The proposed models show less computational load and deliver better results. This study uses the WSJ0 database where clean sentences from WSJ0 are mixed with different background noises to create noisy mixtures. The results show that STOI and PESQ are improved by 21.1% and 1.25 (41.5%) on the WSJ0 database whereas, on the VoiceBank+DEMAND database, STOI and PESQ are imp4.1% and 1.24 (38.6%) respectively. The extension of the models shows further improvement in STOI and PESQ in seen and unseen noisy conditions.

在实时应用中,语音增强(SE)的目标是在保证计算效率和近即时输出的同时实现最佳性能。许多深度神经模型在语音质量和可理解性方面都达到了最佳性能。然而,在资源有限的设备上制定高效、紧凑的深度神经模型进行实时处理仍然是一个挑战。本研究提出了一个紧凑的神经网络模型,设计在复频域用于语音增强,优化为资源有限的设备。该模型结合了卷积编码器-解码器和循环架构,有效地从噪声语音中学习复杂映射,实现实时语音增强,实现低延迟因果处理。循环架构,如长短期内存(LSTM)、门控循环单元(GRU)和简单循环单元(SRU),被作为瓶颈来捕获时间依赖性并提高SE的性能。通过在复频域中表示语音,该模型同时处理幅值和相位信息。此外,本研究扩展了所提出的模型,并引入了基于注意门的跳过连接,使模型能够关注相关信息并动态权衡重要特征。结果表明,所提出的模型优于现有的基准模型,获得了更好的语音质量和可理解性。所提出的模型计算量小,结果好。本研究使用WSJ0数据库,其中来自WSJ0的干净句子与不同的背景噪声混合以产生噪声混合物。结果表明,在WSJ0数据库上STOI和PESQ分别提高了21.1%和1.25(41.5%),而在VoiceBank+DEMAND数据库上STOI和PESQ分别提高了4.1%和1.24(38.6%)。模型的扩展表明,在可见和不可见噪声条件下,STOI和PESQ得到了进一步的改善。
{"title":"Compact deep neural networks for real-time speech enhancement on resource-limited devices","authors":"Fazal E Wahab ,&nbsp;Zhongfu Ye ,&nbsp;Nasir Saleem ,&nbsp;Rizwan Ullah","doi":"10.1016/j.specom.2023.103008","DOIUrl":"https://doi.org/10.1016/j.specom.2023.103008","url":null,"abstract":"<div><p>In real-time applications, the aim of speech enhancement (SE) is to achieve optimal performance while ensuring computational efficiency and near-instant outputs. Many deep neural models have achieved optimal performance in terms of speech quality and intelligibility. However, formulating efficient and compact deep neural models for real-time processing on resource-limited devices remains a challenge. This study presents a compact neural model designed in a complex frequency domain for speech enhancement, optimized for resource-limited devices. The proposed model combines convolutional encoder–decoder and recurrent architectures to effectively learn complex mappings from noisy speech for real-time speech enhancement, enabling low-latency causal processing. Recurrent architectures such as Long-Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and Simple Recurrent Unit (SRU), are incorporated as bottlenecks to capture temporal dependencies and improve the performance of SE. By representing the speech in the complex frequency domain, the proposed model processes both magnitude and phase information. Further, this study extends the proposed models and incorporates attention-gate-based skip connections, enabling the models to focus on relevant information and dynamically weigh the important features. The results show that the proposed models outperform the recent benchmark models and obtain better speech quality and intelligibility. The proposed models show less computational load and deliver better results. This study uses the WSJ0 database where clean sentences from WSJ0 are mixed with different background noises to create noisy mixtures. The results show that STOI and PESQ are improved by 21.1% and 1.25 (41.5%) on the WSJ0 database whereas, on the VoiceBank+DEMAND database, STOI and PESQ are imp4.1% and 1.24 (38.6%) respectively. The extension of the models shows further improvement in STOI and PESQ in seen and unseen noisy conditions.</p></div>","PeriodicalId":49485,"journal":{"name":"Speech Communication","volume":"156 ","pages":"Article 103008"},"PeriodicalIF":3.2,"publicationDate":"2023-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0167639323001425/pdfft?md5=4520d0cf6044eb3b8b478a4f2214ba07&pid=1-s2.0-S0167639323001425-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138413116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Detecting Wilson's disease from unstructured connected speech: An embedding-based approach augmented by attention and bi-directional dependency 从非结构化连接语音中检测威尔逊氏病:一种基于嵌入的方法,增强了注意力和双向依赖
IF 3.2 3区 计算机科学 Q2 ACOUSTICS Pub Date : 2023-11-17 DOI: 10.1016/j.specom.2023.103011
Zhenglin Zhang , Li-Zhuang Yang , Xun Wang , Hongzhi Wang , Stephen T.C. Wong , Hai Li

Wilson's disease (WD) is a neurodegenerative genetic disorder in which dysarthria is the initial neurological symptom. Automated WD diagnosis from speech is thus a promising and clinically valuable approach. The present study investigates the feasibility of WD detection from unstructured connected speech (UCS) using the embedding-based approach augmented by the attention mechanism and bi-directional dependency. The classification experiment was conducted with a sample of 55 WD patients and 55 matched healthy individuals. We compare the proposed embedding approach with two models: the baseline method using the structured task and the model using conventional acoustic features. Results show that the embedding-based model achieves the best accuracy of 90.3 %, which is 4.2 % and 7 % better than the baseline and acoustic approaches, respectively. The bi-directional semantic dependency and attention mechanism can significantly improve detection performance. Moreover, we reveal that the duration of the UCS task affects the model performance, with favorable results achieved using approximately 30 s epochs. Our method provides new insights into the detection of dysarthria-related disorders.

威尔逊氏病(WD)是一种神经退行性遗传疾病,其中构音障碍是最初的神经症状。因此,从语音中自动诊断WD是一种有前途和临床价值的方法。本研究利用基于嵌入的方法,结合注意机制和双向依赖,探讨了从非结构化连接语音(UCS)中检测WD的可行性。分类实验以55例WD患者和55例匹配的健康个体为样本。我们将所提出的嵌入方法与两种模型进行了比较:使用结构化任务的基线方法和使用常规声学特征的模型。结果表明,基于嵌入的模型达到了90.3%的最佳精度,比基线方法和声学方法分别提高了4.2%和7%。双向语义依赖和注意机制可以显著提高检测性能。此外,我们发现UCS任务的持续时间会影响模型的性能,使用大约30秒的时间就可以获得良好的结果。我们的方法为构音障碍相关疾病的检测提供了新的见解。
{"title":"Detecting Wilson's disease from unstructured connected speech: An embedding-based approach augmented by attention and bi-directional dependency","authors":"Zhenglin Zhang ,&nbsp;Li-Zhuang Yang ,&nbsp;Xun Wang ,&nbsp;Hongzhi Wang ,&nbsp;Stephen T.C. Wong ,&nbsp;Hai Li","doi":"10.1016/j.specom.2023.103011","DOIUrl":"https://doi.org/10.1016/j.specom.2023.103011","url":null,"abstract":"<div><p>Wilson's disease (WD) is a neurodegenerative genetic disorder in which dysarthria is the initial neurological symptom. Automated WD diagnosis from speech is thus a promising and clinically valuable approach. The present study investigates the feasibility of WD detection from unstructured connected speech (UCS) using the embedding-based approach augmented by the attention mechanism and bi-directional dependency. The classification experiment was conducted with a sample of 55 WD patients and 55 matched healthy individuals. We compare the proposed embedding approach with two models: the baseline method using the structured task and the model using conventional acoustic features. Results show that the embedding-based model achieves the best accuracy of 90.3 %, which is 4.2 % and 7 % better than the baseline and acoustic approaches, respectively. The bi-directional semantic dependency and attention mechanism can significantly improve detection performance. Moreover, we reveal that the duration of the UCS task affects the model performance, with favorable results achieved using approximately 30 s epochs. Our method provides new insights into the detection of dysarthria-related disorders.</p></div>","PeriodicalId":49485,"journal":{"name":"Speech Communication","volume":"156 ","pages":"Article 103011"},"PeriodicalIF":3.2,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0167639323001450/pdfft?md5=f433bbc4cd8c673c67c80300ad3c60c4&pid=1-s2.0-S0167639323001450-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138448357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Speech Communication
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1