今天跟大家分享一篇语音相关的论文合集：cs.SD语音6篇，eess.AS音频处理6篇。
【1】 TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation
标题：TF-GridNet：使单声道说话人分离的时频域模型再次变得更好
链接：https://arxiv.org/abs/2209.03952
作者：Zhong-Qiu Wang,Samuele Cornell,Shukjae Choi,Younglo Lee,Byeong-Yeol Kim,Shinji Watanabe机构：Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA, Italy, AIRS Company, Hyundai Motor Group, Seoul, Korea摘要：提出了一种新的时频域多路径深度神经网络TF-GridNet，用于无回声条件下的单声道说话人无关说话人分离。该模型将多个多径块堆叠起来，每个多径块由帧内频谱模块、子带时间模块和全带自注意模块组成，以利用局部和全局频谱—时间信息进行分离。该模型被训练以执行复谱映射，其中输入混合物的实部和虚部（RI）分量被堆叠作为输入特征以预测目标RI分量。除了使用尺度不变的信号失真比（SI-SDR）损失进行模型训练外，我们还包括一个新的损失项，以鼓励分离的源加入到输入混合物中。在不使用动态混合的情况下，我们在WSJ0-2mix数据集上获得了23.4 dB SI-SDR改善（SI-SDRi），大大超过了之前的最佳性能。摘要：We propose TF-GridNet, a novel multi-path deep neural network (DNN) operating in the time-frequency (T-F) domain, for monaural talker-independent speaker separation in anechoic conditions. The model stacks several multi-path blocks, each consisting of an intra-frame spectral module, a sub-band temporal module, and a full-band self-attention module, to leverage local and global spectro-temporal information for separation. The model is trained to perform complex spectral mapping, where the real and imaginary (RI) components of the input mixture are stacked as input features to predict the target RI components. Besides using the scale-invariant signal-to-distortion ratio (SI-SDR) loss for model training, we include a novel loss term to encourage the separated sources to add up to the input mixture. Without using dynamic mixing, we obtain 23.4 dB SI-SDR improvement (SI-SDRi) on the WSJ0-2mix dataset, outperforming the previous best by a large margin.
【2】 Dyadic Interaction Assessment from Free-living Audio for Depression Severity Assessment
标题：来自自由生活音频的二元交互评估用于抑郁症严重程度评估
链接：https://arxiv.org/abs/2209.03901
作者：Bishal Lamichhane,Nidal Moukaddam,Ankit B. Patel,Ashutosh Sabharwal机构：ECE, Rice University, Houston, Texas, USA, Menninger Department of Psychiatry, Baylor College of Medicine, Houston, Texas, USA.备注：Accepted to INTERSPEECH 2022摘要：抑郁症中精神运动性迟缓与二元临床访谈中言语时序变化相关。在这项工作中，我们研究了自由生活的二元互动的言语时序特征。除了可能进行连续监测以补充临床访视外，在自由生活条件下进行的研究还可以推断社交特征，如抑郁症中涉及的二元互动频率。在DIHARD数据集中，我们采用说话人计数估计器作为二元交互检测器，特异性为89.5%，灵敏度为86.1%。使用该检测器，我们从32个参与者的多日音频记录中检测到的二元交互中获得了语音定时特征，这些参与者包括13个健康个体、11个抑郁个体和8个精神障碍个体。在无抑郁症或轻度抑郁症的受试者中，二元互动频率随抑郁症严重程度的增加而增加，表明这是抑郁症发作的一个潜在诊断标志物。然而，对于中度或重度抑郁症的参与者，二元互动频率随着抑郁症严重程度的增加而降低。在言语时间特征方面，反应时与抑郁严重程度呈显著正相关。我们的工作显示了从自由生活的录音中进行二元互动分析以获得抑郁严重程度标志物的潜力。摘要：Psychomotor retardation in depression has been associated with speech timing changes from dyadic clinical interviews. In this work, we investigate speech timing features from free-living dyadic interactions. Apart from the possibility of continuous monitoring to complement clinical visits, a study in free-living conditions would also allow inferring sociability features such as dyadic interaction frequency implicated in depression. We adapted a speaker count estimator as a dyadic interaction detector with a specificity of 89.5% and a sensitivity of 86.1% in the DIHARD dataset. Using the detector, we obtained speech timing features from the detected dyadic interactions in multi-day audio recordings of 32 participants comprised of 13 healthy individuals, 11 individuals with depression, and 8 individuals with psychotic disorders. The dyadic interaction frequency increased with depression severity in participants with no or mild depression, indicating a potential diagnostic marker of depression onset. However, the dyadic interaction frequency decreased with increasing depression severity for participants with moderate or severe depression. In terms of speech timing features, the response time had a significant positive correlation with depression severity. Our work shows the potential of dyadic interaction analysis from audio recordings of free-living to obtain markers of depression severity.
【3】 Hardware Accelerator and Neural Network Co-Optimization for Ultra-Low-Power Audio Processing Devices
标题：超低功耗音频处理设备的硬件加速器和神经网络联合优化
链接：https://arxiv.org/abs/2209.03807
作者：Christoph Gerum,Adrian Frischknecht,Tobias Hald,Paul Palomero Bernardo,Konstantin Lübeck,Olver Bringmann机构：Hardware Accelerator and Neural NetworkCo-Optimization for Ultra-Low-Power AudioProcessing DevicesGerum ChristophDepartment of Computer ScienceUniversity of T¨ubingenchristoph备注：Accepted Version for: EUROMICRO DSD 2022摘要：人工神经网络的日益普及并不局限于超低功耗边缘器件。然而，这些通常具有高计算需求，并且需要专门的硬件加速器来确保设计满足功率和性能限制。人工优化神经网络以及相应的硬件加速器可能非常具有挑战性。本文介绍了HANNAH（Hardware Accelerator and Neural Network seArcH），这是一个用于资源和功耗受限的边缘设备的深度神经网络和硬件加速器的自动化和软硬件协同设计的框架。该优化方法使用基于进化的搜索算法、神经网络模板技术和用于可配置的UltraTrail硬件加速器模板的分析KPI模型，以找到优化的神经网络和加速器配置。实验结果表明，HANNAH算法能够在单类唤醒词检测、多类关键词检测和语音活动检测等不同的音频分类任务中，以最小的功耗和较高的准确率找到合适的神经网络，优于相关工作.摘要：The increasing spread of artificial neural networks does not stop at ultralow-power edge devices. However, these very often have high computational demand and require specialized hardware accelerators to ensure the design meets power and performance constraints. The manual optimization of neural networks along with the corresponding hardware accelerators can be very challenging. This paper presents HANNAH (Hardware Accelerator and Neural Network seArcH), a framework for automated and combined hardware/software co-design of deep neural networks and hardware accelerators for resource and power-constrained edge devices. The optimization approach uses an evolution-based search algorithm, a neural network template technique, and analytical KPI models for the configurable UltraTrail hardware accelerator template to find an optimized neural network and accelerator configuration. We demonstrate that HANNAH can find suitable neural networks with minimized power consumption and high accuracy for different audio classification tasks such as single-class wake word detection, multi-class keyword detection, and voice activity detection, which are superior to the related work.
【4】 Accented Speech Recognition under the Indian context
标题：印度语境下的重音语音识别
链接：https://arxiv.org/abs/2209.03787
机构：Under the supervision of:, Dr. Vaishali Yadav & Dr. Chiranjeevi Yarra, Department of Computer and Communication Engineering, School of Computing and Information Technology, Manipal University Jaipur, VPO. Dehmi Kalan, Jaipur, Rajasthan, India –备注：33 pages, 24 Figures, 1 Table摘要：口音是识别文化、情感、行为等不可或缺的一部分。人们经常因为口音而以不同的方式看待彼此。口音本身可以是地位、自豪感和其他情感信息的传达者，这些信息可以通过言语本身来捕捉。重音本身可以定义为：“特定地区、国家或社会群体中的人们发音的方式”或“给予单词中的音节、句子中的单词或一组音符中的音符的特殊强调”。重音语音识别是语音识别领域的一个重要课题。语音识别是计算机科学和语言学研究的一个跨学科子领域，其主要目标是开发能够将语音转换为文本的技术。语音可以是任何形式，例如朗读语音或自发语音、会话语音。言语与文字不同，有很多多样性。这种多样性源于环境条件、说话者之间的差异、信道噪声、由于残疾而导致的言语产生的差异、不流利的存在。因此，言语确实是一个有待开发的丰富的信息来源。摘要：Accent forms an integral part of identifying cultures, emotions,behavior's, etc. People often perceive each other in a different manner due to their accent. The accent itself can be a conveyor of status, pride, and other emotional information which can be captured through Speech itself. Accent itself can be defined as: "the way in which people in a particular area, country, or social group pronounce words" or "a special emphasis given to a syllable in a word, word in a sentence, or note in a set of musical notes". Accented Speech Recognition is one the most important problems in the domain of Speech Recognition. Speech recognition is an interdisciplinary sub-field of Computer Science and Linguistics research where the main aim is to develop technologies which enable conversion of speech into text. The speech can be of any form such as read speech or spontaneous speech, conversational speech. Speech unlike text has lot of diversity. This diversity stems from the environmental conditions, variabilities from speaker to speaker, channel noise, differences in Speech production due to disabilities, presence of disfluencies. Speech therefore is indeed a rich source of information waiting to be exploited.
【5】 Developing a multi-variate prediction model for the detection of COVID-19 from Crowd-sourced Respiratory Voice Data
标题：从人群呼吸道语音数据中建立新冠肺炎检测的多变量预测模型
链接：https://arxiv.org/abs/2209.03727
作者：Wafaa Aljbawi,Sami O. Simmons,Visara Urovi机构：We used the Cambridge University dataset consisting of 89 3 audio samples备注：9 pages, 6 figures, poster presented at the European Respiratory Society, Barcelona, September 2022摘要：COVID-19已经影响到全球超过223个国家。目前迫切需要非侵入性、低成本和高度可扩展的解决方案来检测COVID-19，特别是在PCR检测无法普及的低资源国家。我们的目标是利用普通人群通过个人设备自发提供的语音数据录音（语音录音和简短问卷），开发一种识别COVID-19的深度学习模型。这项工作的新颖之处在于开发了一种深度学习模型，用于从语音记录中识别新冠肺炎患者。方法：我们使用剑桥大学的数据集，该数据集包含893个音频样本，来自4352名使用COVID-19 Sounds应用程序的参与者。使用Mel谱图分析提取语音特征。基于语音数据，我们开发了深度学习分类模型来检测COVID-19阳性病例。这些模型包括长—短时记忆（LSTM）和卷积神经网络（CNN）。我们将其预测能力与基线分类模型（即逻辑回归和支持向量机）进行了比较。结果：基于Mel频率倒谱系数（MFCC）特征的LSTM达到了最高的准确率（89%），灵敏度和特异性分别为89%和89%，与现有技术中获得的结果相比，使用所提出的模型获得的结果表明COVID-19诊断的预测准确率显著提高。结论：深度学习可以检测COVID-19患者声音中的细微变化，结果令人鼓舞。作为对当前测试技术的补充，该模型可能有助于卫生专业人员使用简单的语音分析快速诊断和追踪新冠肺炎病例摘要：COVID-19 has affected more than 223 countries worldwide. There is a pressing need for non invasive, low costs and highly scalable solutions to detect COVID-19, especially in low-resource countries where PCR testing is not ubiquitously available. Our aim is to develop a deep learning model identifying COVID-19 using voice data recordings spontaneously provided by the general population (voice recordings and a short questionnaire) via their personal devices. The novelty of this work is in the development of a deep learning model for the identification of COVID-19 patients from voice recordings. Methods: We used the Cambridge University dataset consisting of 893 audio samples, crowd-sourced from 4352 participants that used a COVID-19 Sounds app. Voice features were extracted using a Mel-spectrogram analysis. Based on the voice data, we developed deep learning classification models to detect positive COVID-19 cases. These models included Long-Short Term Memory (LSTM) and Convolutional Neural Network (CNN). We compared their predictive power to baseline classification models, namely Logistic Regression and Support Vector Machine. Results: LSTM based on a Mel-frequency cepstral coefficients (MFCC) features achieved the highest accuracy (89%,) with a sensitivity and specificity of respectively 89% and 89%, The results achieved with the proposed model suggest a significant improvement in the prediction accuracy of COVID-19 diagnosis compared to the results obtained in the state of the art. Conclusion: Deep learning can detect subtle changes in the voice of COVID-19 patients with promising results. As an addition to the current testing techniques this model may aid health professionals in fast diagnosis and tracing of COVID-19 cases using simple voice analysis
【6】 What Did I Just Hear? Detecting Pornographic Sounds in Adult Videos Using Neural Networks
标题：我刚才听到了什么？基于神经网络的成人视频色情声音检测
链接：https://arxiv.org/abs/2209.03711
作者：Holy Lovenia,Dessi Puji Lestari,Rita Frieske机构：Prosa.ai, Bandung Institute of Technology, The Hong Kong University of Science, and Technology (HKUST)备注：Published in AudioMostly 2022, ACM摘要：基于音频的色情检测通过利用独特的频谱特征，实现了高效的成人内容过滤，而不会牺牲性能。为了改进这一方法，我们探索了基于不同神经结构和声学特征的色情声音建模方法。我们发现，在Pornography-800数据集上，基于log mel谱图训练的CNN取得了最好的性能。实验结果还表明，logmel谱图能更好地表征模型对色情声音的识别能力。最后，为了对整个音频波形而不是片段进行分类，我们采用了产生最佳音频电平检测结果的投票片段到音频技术。摘要：Audio-based pornographic detection enables efficient adult content filtering without sacrificing performance by exploiting distinct spectral characteristics. To improve it, we explore pornographic sound modeling based on different neural architectures and acoustic features. We find that CNN trained on log mel spectrogram achieves the best performance on Pornography-800 dataset. Our experiment results also show that log mel spectrogram allows better representations for the models to recognize pornographic sounds. Finally, to classify whole audio waveforms rather than segments, we employ voting segment-to-audio technique that yields the best audio-level detection results.【1】 TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation
标题：TF-GridNet：使单声道说话人分离的时频域模型再次变得更好
链接：https://arxiv.org/abs/2209.03952
* 与cs.SD语音【1】为同一篇
作者：Zhong-Qiu Wang,Samuele Cornell,Shukjae Choi,Younglo Lee,Byeong-Yeol Kim,Shinji Watanabe机构：Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA, Italy, AIRS Company, Hyundai Motor Group, Seoul, Korea摘要：提出了一种新的时频域多路径深度神经网络TF-GridNet，用于无回声条件下的单声道说话人无关说话人分离。该模型将多个多径块堆叠起来，每个多径块由帧内频谱模块、子带时间模块和全带自注意模块组成，以利用局部和全局频谱—时间信息进行分离。该模型被训练以执行复谱映射，其中输入混合物的实部和虚部（RI）分量被堆叠作为输入特征以预测目标RI分量。除了使用尺度不变的信号失真比（SI-SDR）损失进行模型训练外，我们还包括一个新的损失项，以鼓励分离的源加入到输入混合物中。在不使用动态混合的情况下，我们在WSJ0-2mix数据集上获得了23.4 dB SI-SDR改善（SI-SDRi），大大超过了之前的最佳性能。摘要：We propose TF-GridNet, a novel multi-path deep neural network (DNN) operating in the time-frequency (T-F) domain, for monaural talker-independent speaker separation in anechoic conditions. The model stacks several multi-path blocks, each consisting of an intra-frame spectral module, a sub-band temporal module, and a full-band self-attention module, to leverage local and global spectro-temporal information for separation. The model is trained to perform complex spectral mapping, where the real and imaginary (RI) components of the input mixture are stacked as input features to predict the target RI components. Besides using the scale-invariant signal-to-distortion ratio (SI-SDR) loss for model training, we include a novel loss term to encourage the separated sources to add up to the input mixture. Without using dynamic mixing, we obtain 23.4 dB SI-SDR improvement (SI-SDRi) on the WSJ0-2mix dataset, outperforming the previous best by a large margin.
【2】 Dyadic Interaction Assessment from Free-living Audio for Depression Severity Assessment
标题：来自自由生活音频的二元交互评估用于抑郁症严重程度评估
链接：https://arxiv.org/abs/2209.03901
* 与cs.SD语音【2】为同一篇
作者：Bishal Lamichhane,Nidal Moukaddam,Ankit B. Patel,Ashutosh Sabharwal机构：ECE, Rice University, Houston, Texas, USA, Menninger Department of Psychiatry, Baylor College of Medicine, Houston, Texas, USA.备注：Accepted to INTERSPEECH 2022摘要：抑郁症中精神运动性迟缓与二元临床访谈中言语时序变化相关。在这项工作中，我们研究了自由生活的二元互动的言语时序特征。除了可能进行连续监测以补充临床访视外，在自由生活条件下进行的研究还可以推断社交特征，如抑郁症中涉及的二元互动频率。在DIHARD数据集中，我们采用说话人计数估计器作为二元交互检测器，特异性为89.5%，灵敏度为86.1%。使用该检测器，我们从32个参与者的多日音频记录中检测到的二元交互中获得了语音定时特征，这些参与者包括13个健康个体、11个抑郁个体和8个精神障碍个体。在无抑郁症或轻度抑郁症的受试者中，二元互动频率随抑郁症严重程度的增加而增加，表明这是抑郁症发作的一个潜在诊断标志物。然而，对于中度或重度抑郁症的参与者，二元互动频率随着抑郁症严重程度的增加而降低。在言语时间特征方面，反应时与抑郁严重程度呈显著正相关。我们的工作显示了从自由生活的录音中进行二元互动分析以获得抑郁严重程度标志物的潜力。摘要：Psychomotor retardation in depression has been associated with speech timing changes from dyadic clinical interviews. In this work, we investigate speech timing features from free-living dyadic interactions. Apart from the possibility of continuous monitoring to complement clinical visits, a study in free-living conditions would also allow inferring sociability features such as dyadic interaction frequency implicated in depression. We adapted a speaker count estimator as a dyadic interaction detector with a specificity of 89.5% and a sensitivity of 86.1% in the DIHARD dataset. Using the detector, we obtained speech timing features from the detected dyadic interactions in multi-day audio recordings of 32 participants comprised of 13 healthy individuals, 11 individuals with depression, and 8 individuals with psychotic disorders. The dyadic interaction frequency increased with depression severity in participants with no or mild depression, indicating a potential diagnostic marker of depression onset. However, the dyadic interaction frequency decreased with increasing depression severity for participants with moderate or severe depression. In terms of speech timing features, the response time had a significant positive correlation with depression severity. Our work shows the potential of dyadic interaction analysis from audio recordings of free-living to obtain markers of depression severity.
【3】 Hardware Accelerator and Neural Network Co-Optimization for Ultra-Low-Power Audio Processing Devices
标题：超低功耗音频处理设备的硬件加速器和神经网络联合优化
链接：https://arxiv.org/abs/2209.03807
* 与cs.SD语音【3】为同一篇
作者：Christoph Gerum,Adrian Frischknecht,Tobias Hald,Paul Palomero Bernardo,Konstantin Lübeck,Olver Bringmann机构：Hardware Accelerator and Neural NetworkCo-Optimization for Ultra-Low-Power AudioProcessing DevicesGerum ChristophDepartment of Computer ScienceUniversity of T¨ubingenchristoph备注：Accepted Version for: EUROMICRO DSD 2022摘要：人工神经网络的日益普及并不局限于超低功耗边缘器件。然而，这些通常具有高计算需求，并且需要专门的硬件加速器来确保设计满足功率和性能限制。人工优化神经网络以及相应的硬件加速器可能非常具有挑战性。本文介绍了HANNAH（Hardware Accelerator and Neural Network seArcH），这是一个用于资源和功耗受限的边缘设备的深度神经网络和硬件加速器的自动化和软硬件协同设计的框架。该优化方法使用基于进化的搜索算法、神经网络模板技术和用于可配置的UltraTrail硬件加速器模板的分析KPI模型，以找到优化的神经网络和加速器配置。实验结果表明，HANNAH算法能够在单类唤醒词检测、多类关键词检测和语音活动检测等不同的音频分类任务中，以最小的功耗和较高的准确率找到合适的神经网络，优于相关工作.摘要：The increasing spread of artificial neural networks does not stop at ultralow-power edge devices. However, these very often have high computational demand and require specialized hardware accelerators to ensure the design meets power and performance constraints. The manual optimization of neural networks along with the corresponding hardware accelerators can be very challenging. This paper presents HANNAH (Hardware Accelerator and Neural Network seArcH), a framework for automated and combined hardware/software co-design of deep neural networks and hardware accelerators for resource and power-constrained edge devices. The optimization approach uses an evolution-based search algorithm, a neural network template technique, and analytical KPI models for the configurable UltraTrail hardware accelerator template to find an optimized neural network and accelerator configuration. We demonstrate that HANNAH can find suitable neural networks with minimized power consumption and high accuracy for different audio classification tasks such as single-class wake word detection, multi-class keyword detection, and voice activity detection, which are superior to the related work.
【4】 Accented Speech Recognition under the Indian context
标题：印度语境下的重音语音识别
链接：https://arxiv.org/abs/2209.03787
* 与cs.SD语音【4】为同一篇
机构：Under the supervision of:, Dr. Vaishali Yadav & Dr. Chiranjeevi Yarra, Department of Computer and Communication Engineering, School of Computing and Information Technology, Manipal University Jaipur, VPO. Dehmi Kalan, Jaipur, Rajasthan, India –备注：33 pages, 24 Figures, 1 Table摘要：口音是识别文化、情感、行为等不可或缺的一部分。人们经常因为口音而以不同的方式看待彼此。口音本身可以是地位、自豪感和其他情感信息的传达者，这些信息可以通过言语本身来捕捉。重音本身可以定义为：“特定地区、国家或社会群体中的人们发音的方式”或“给予单词中的音节、句子中的单词或一组音符中的音符的特殊强调”。重音语音识别是语音识别领域的一个重要课题。语音识别是计算机科学和语言学研究的一个跨学科子领域，其主要目标是开发能够将语音转换为文本的技术。语音可以是任何形式，例如朗读语音或自发语音、会话语音。言语与文字不同，有很多多样性。这种多样性源于环境条件、说话者之间的差异、信道噪声、由于残疾而导致的言语产生的差异、不流利的存在。因此，言语确实是一个有待开发的丰富的信息来源。摘要：Accent forms an integral part of identifying cultures, emotions,behavior's, etc. People often perceive each other in a different manner due to their accent. The accent itself can be a conveyor of status, pride, and other emotional information which can be captured through Speech itself. Accent itself can be defined as: "the way in which people in a particular area, country, or social group pronounce words" or "a special emphasis given to a syllable in a word, word in a sentence, or note in a set of musical notes". Accented Speech Recognition is one the most important problems in the domain of Speech Recognition. Speech recognition is an interdisciplinary sub-field of Computer Science and Linguistics research where the main aim is to develop technologies which enable conversion of speech into text. The speech can be of any form such as read speech or spontaneous speech, conversational speech. Speech unlike text has lot of diversity. This diversity stems from the environmental conditions, variabilities from speaker to speaker, channel noise, differences in Speech production due to disabilities, presence of disfluencies. Speech therefore is indeed a rich source of information waiting to be exploited.
【5】 Developing a multi-variate prediction model for the detection of COVID-19 from Crowd-sourced Respiratory Voice Data
标题：从人群呼吸道语音数据中建立新冠肺炎检测的多变量预测模型
链接：https://arxiv.org/abs/2209.03727
* 与cs.SD语音【5】为同一篇
作者：Wafaa Aljbawi,Sami O. Simmons,Visara Urovi机构：We used the Cambridge University dataset consisting of 89 3 audio samples备注：9 pages, 6 figures, poster presented at the European Respiratory Society, Barcelona, September 2022摘要：COVID-19已经影响到全球超过223个国家。目前迫切需要非侵入性、低成本和高度可扩展的解决方案来检测COVID-19，特别是在PCR检测无法普及的低资源国家。我们的目标是利用普通人群通过个人设备自发提供的语音数据录音（语音录音和简短问卷），开发一种识别COVID-19的深度学习模型。这项工作的新颖之处在于开发了一种深度学习模型，用于从语音记录中识别新冠肺炎患者。方法：我们使用剑桥大学的数据集，该数据集包含893个音频样本，来自4352名使用COVID-19 Sounds应用程序的参与者。使用Mel谱图分析提取语音特征。基于语音数据，我们开发了深度学习分类模型来检测COVID-19阳性病例。这些模型包括长—短时记忆（LSTM）和卷积神经网络（CNN）。我们将其预测能力与基线分类模型（即逻辑回归和支持向量机）进行了比较。结果：基于Mel频率倒谱系数（MFCC）特征的LSTM达到了最高的准确率（89%），灵敏度和特异性分别为89%和89%，与现有技术中获得的结果相比，使用所提出的模型获得的结果表明COVID-19诊断的预测准确率显著提高。结论：深度学习可以检测COVID-19患者声音中的细微变化，结果令人鼓舞。作为对当前测试技术的补充，该模型可能有助于卫生专业人员使用简单的语音分析快速诊断和追踪新冠肺炎病例摘要：COVID-19 has affected more than 223 countries worldwide. There is a pressing need for non invasive, low costs and highly scalable solutions to detect COVID-19, especially in low-resource countries where PCR testing is not ubiquitously available. Our aim is to develop a deep learning model identifying COVID-19 using voice data recordings spontaneously provided by the general population (voice recordings and a short questionnaire) via their personal devices. The novelty of this work is in the development of a deep learning model for the identification of COVID-19 patients from voice recordings. Methods: We used the Cambridge University dataset consisting of 893 audio samples, crowd-sourced from 4352 participants that used a COVID-19 Sounds app. Voice features were extracted using a Mel-spectrogram analysis. Based on the voice data, we developed deep learning classification models to detect positive COVID-19 cases. These models included Long-Short Term Memory (LSTM) and Convolutional Neural Network (CNN). We compared their predictive power to baseline classification models, namely Logistic Regression and Support Vector Machine. Results: LSTM based on a Mel-frequency cepstral coefficients (MFCC) features achieved the highest accuracy (89%,) with a sensitivity and specificity of respectively 89% and 89%, The results achieved with the proposed model suggest a significant improvement in the prediction accuracy of COVID-19 diagnosis compared to the results obtained in the state of the art. Conclusion: Deep learning can detect subtle changes in the voice of COVID-19 patients with promising results. As an addition to the current testing techniques this model may aid health professionals in fast diagnosis and tracing of COVID-19 cases using simple voice analysis
【6】 What Did I Just Hear? Detecting Pornographic Sounds in Adult Videos Using Neural Networks
标题：我刚才听到了什么？基于神经网络的成人视频色情声音检测
链接：https://arxiv.org/abs/2209.03711
* 与cs.SD语音【6】为同一篇
作者：Holy Lovenia,Dessi Puji Lestari,Rita Frieske机构：Prosa.ai, Bandung Institute of Technology, The Hong Kong University of Science, and Technology (HKUST)备注：Published in AudioMostly 2022, ACM摘要：基于音频的色情检测通过利用独特的频谱特征，实现了高效的成人内容过滤，而不会牺牲性能。为了改进这一方法，我们探索了基于不同神经结构和声学特征的色情声音建模方法。我们发现，在Pornography-800数据集上，基于log mel谱图训练的CNN取得了最好的性能。实验结果还表明，logmel谱图能更好地表征模型对色情声音的识别能力。最后，为了对整个音频波形而不是片段进行分类，我们采用了产生最佳音频电平检测结果的投票片段到音频技术。摘要：Audio-based pornographic detection enables efficient adult content filtering without sacrificing performance by exploiting distinct spectral characteristics. To improve it, we explore pornographic sound modeling based on different neural architectures and acoustic features. We find that CNN trained on log mel spectrogram achieves the best performance on Pornography-800 dataset. Our experiment results also show that log mel spectrogram allows better representations for the models to recognize pornographic sounds. Finally, to classify whole audio waveforms rather than segments, we employ voting segment-to-audio technique that yields the best audio-level detection results.
机器翻译，仅供参考
每日语音速递