Pub Date : 2023-10-04DOI: 10.1186/s13636-023-00304-8
Elisa Tengan, Thomas Dietzen, Filip Elvander, Toon van Waterschoot
Abstract In this paper, two approaches are proposed for estimating the direction of arrival (DOA) and power spectral density (PSD) of stationary point sources by using a single, rotating, directional microphone. These approaches are based on a method previously presented by the authors, in which point source DOAs were estimated by using a broadband signal model and solving a group-sparse optimization problem, where the number of observations made by the rotating directional microphone can be lower than the number of candidate DOAs in an angular grid. The DOA estimation is followed by the estimation of the sources’ PSDs through the solution of an overdetermined least squares problem. The first approach proposed in this paper includes the use of an additional nonnegativity constraint on the residual noise term when solving the group-sparse optimization problem and is referred to as the Group Lasso Least Squares (GL-LS) approach. The second proposed approach, in addition to the new nonnegativity constraint, employs a narrowband signal model when building the linear system of equations used for formulating the group-sparse optimization problem, where the DOAs and PSDs can be jointly estimated by iterative, group-wise reweighting. This is referred to as the Group-Lasso with $$l_1$$ l1 -reweighting (GL-L1) approach. Both proposed approaches are implemented using the alternating direction method of multipliers (ADMM), and their performance is evaluated through simulations in which different setup conditions are considered, ranging from different types of model mismatch to variations in the acoustic scene and microphone directivity pattern. The results obtained show that in a scenario involving a microphone response mismatch between observed data and the signal model used, having the additional nonnegativity constraint on the residual noise can improve the DOA estimation for the case of GL-LS and the PSD estimation for the case of GL-L1. Moreover, the GL-L1 approach can present an advantage over GL-LS in terms of DOA estimation performance in scenarios with low SNR or where multiple sources are closely located to each other. Finally, it is shown that having the least squares PSD re-estimation step is beneficial in most scenarios, such that GL-LS outperformed GL-L1 in terms of PSD estimation errors.
摘要本文提出了两种利用单旋转定向传声器估计静止点源的到达方向(DOA)和功率谱密度(PSD)的方法。这些方法基于作者先前提出的方法，其中通过使用宽带信号模型和解决组稀疏优化问题来估计点源doa，其中旋转定向麦克风的观测数量可以低于角网格中的候选doa数量。在DOA估计之后，通过求解过定最小二乘问题估计源的psd。本文提出的第一种方法包括在求解群稀疏优化问题时对残余噪声项使用附加的非负性约束，称为群Lasso最小二乘(GL-LS)方法。第二种提出的方法，除了新的非负性约束外，在构建用于制定群稀疏优化问题的线性方程组时采用窄带信号模型，其中doa和psd可以通过迭代，群加权来联合估计。这被称为Group-Lasso with $$l_1$$ 1 -reweighting (GL-L1)方法。这两种方法都使用乘法器的交替方向方法(ADMM)来实现，并通过考虑不同设置条件的仿真来评估它们的性能，这些条件包括不同类型的模型不匹配、声场景和麦克风指向性模式的变化。结果表明，在观测数据与所用信号模型麦克风响应不匹配的情况下，对残差噪声附加非负性约束可以改善GL-LS情况下的DOA估计和GL-L1情况下的PSD估计。此外，GL-L1方法在低信噪比或多个信源彼此靠近的情况下，在DOA估计性能方面比GL-LS方法具有优势。最后，研究表明，在大多数情况下，最小二乘PSD重估计步骤是有益的，因此GL-LS在PSD估计误差方面优于GL-L1。
{"title":"Direction-of-arrival and power spectral density estimation using a single directional microphone and group-sparse optimization","authors":"Elisa Tengan, Thomas Dietzen, Filip Elvander, Toon van Waterschoot","doi":"10.1186/s13636-023-00304-8","DOIUrl":"https://doi.org/10.1186/s13636-023-00304-8","url":null,"abstract":"Abstract In this paper, two approaches are proposed for estimating the direction of arrival (DOA) and power spectral density (PSD) of stationary point sources by using a single, rotating, directional microphone. These approaches are based on a method previously presented by the authors, in which point source DOAs were estimated by using a broadband signal model and solving a group-sparse optimization problem, where the number of observations made by the rotating directional microphone can be lower than the number of candidate DOAs in an angular grid. The DOA estimation is followed by the estimation of the sources’ PSDs through the solution of an overdetermined least squares problem. The first approach proposed in this paper includes the use of an additional nonnegativity constraint on the residual noise term when solving the group-sparse optimization problem and is referred to as the Group Lasso Least Squares (GL-LS) approach. The second proposed approach, in addition to the new nonnegativity constraint, employs a narrowband signal model when building the linear system of equations used for formulating the group-sparse optimization problem, where the DOAs and PSDs can be jointly estimated by iterative, group-wise reweighting. This is referred to as the Group-Lasso with $$l_1$$ <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:msub> <mml:mi>l</mml:mi> <mml:mn>1</mml:mn> </mml:msub> </mml:math> -reweighting (GL-L1) approach. Both proposed approaches are implemented using the alternating direction method of multipliers (ADMM), and their performance is evaluated through simulations in which different setup conditions are considered, ranging from different types of model mismatch to variations in the acoustic scene and microphone directivity pattern. The results obtained show that in a scenario involving a microphone response mismatch between observed data and the signal model used, having the additional nonnegativity constraint on the residual noise can improve the DOA estimation for the case of GL-LS and the PSD estimation for the case of GL-L1. Moreover, the GL-L1 approach can present an advantage over GL-LS in terms of DOA estimation performance in scenarios with low SNR or where multiple sources are closely located to each other. Finally, it is shown that having the least squares PSD re-estimation step is beneficial in most scenarios, such that GL-LS outperformed GL-L1 in terms of PSD estimation errors.","PeriodicalId":49309,"journal":{"name":"Journal on Audio Speech and Music Processing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135590949","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}
Pub Date : 2023-09-21DOI: 10.1186/s13636-023-00296-5
Santiago Ruiz, Toon van Waterschoot, Marc Moonen
Abstract This paper presents three cascade algorithms for combined acoustic feedback cancelation (AFC) and noise reduction (NR) in speech applications. A prediction error method (PEM)-based adaptive feedback cancelation (PEM-based AFC) algorithm is used for the AFC stage, while a multichannel Wiener filter (MWF) is applied for the NR stage. A scenario with M microphones and 1 loudspeaker is considered, without loss of generality. The first algorithm is the baseline algorithm, namely the cascade M -channel rank-1 MWF and PEM-AFC, where a NR stage is performed first using a rank-1 MWF followed by a single-channel AFC stage using a PEM-based AFC algorithm. The second algorithm is the cascade $$(M+1)$$ (M+1) -channel rank-2 MWF and PEM-AFC, where again a NR stage is applied first followed by a single-channel AFC stage. The novelty of this algorithm is to consider an ( $$M+1$$ M+1 )-channel data model in the MWF formulation with two different desired signals, i.e., the speech component in the reference microphone signal and in the loudspeaker signal, both defined by the speech source signal but not equal to each other. The two desired signal estimates are later used in a single-channel PEM-based AFC stage. The third algorithm is the cascade M -channel PEM-AFC and rank-1 MWF where an M -channel AFC stage is performed first followed by an M -channel NR stage. Although in cascade algorithms where NR is performed first and then AFC the estimation of the feedback path is usually affected by the NR stage, it is shown here that by performing a rank-2 approximation of the speech correlation matrix this issue can be avoided and the feedback path can be correctly estimated. The performance of the algorithms is assessed by means of closed-loop simulations where it is shown that for the considered input signal-to-noise ratios (iSNRs) the cascade $$(M+1)$$ (M+1) -channel rank-2 MWF and PEM-AFC and the cascade M -channel PEM-AFC and rank-1 MWF algorithms outperform the cascade M -channel rank-1 MWF and PEM-AFC algorithm in terms of the added stable gain (ASG) and misadjustment (Mis) as well as in terms of perceptual metrics such as the short-time objective intelligibility (STOI), perceptual evaluation of speech quality (PESQ), and signal distortion (SD).
{"title":"Cascade algorithms for combined acoustic feedback cancelation and noise reduction","authors":"Santiago Ruiz, Toon van Waterschoot, Marc Moonen","doi":"10.1186/s13636-023-00296-5","DOIUrl":"https://doi.org/10.1186/s13636-023-00296-5","url":null,"abstract":"Abstract This paper presents three cascade algorithms for combined acoustic feedback cancelation (AFC) and noise reduction (NR) in speech applications. A prediction error method (PEM)-based adaptive feedback cancelation (PEM-based AFC) algorithm is used for the AFC stage, while a multichannel Wiener filter (MWF) is applied for the NR stage. A scenario with M microphones and 1 loudspeaker is considered, without loss of generality. The first algorithm is the baseline algorithm, namely the cascade M -channel rank-1 MWF and PEM-AFC, where a NR stage is performed first using a rank-1 MWF followed by a single-channel AFC stage using a PEM-based AFC algorithm. The second algorithm is the cascade $$(M+1)$$ <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:mrow> <mml:mo>(</mml:mo> <mml:mi>M</mml:mi> <mml:mo>+</mml:mo> <mml:mn>1</mml:mn> <mml:mo>)</mml:mo> </mml:mrow> </mml:math> -channel rank-2 MWF and PEM-AFC, where again a NR stage is applied first followed by a single-channel AFC stage. The novelty of this algorithm is to consider an ( $$M+1$$ <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:mrow> <mml:mi>M</mml:mi> <mml:mo>+</mml:mo> <mml:mn>1</mml:mn> </mml:mrow> </mml:math> )-channel data model in the MWF formulation with two different desired signals, i.e., the speech component in the reference microphone signal and in the loudspeaker signal, both defined by the speech source signal but not equal to each other. The two desired signal estimates are later used in a single-channel PEM-based AFC stage. The third algorithm is the cascade M -channel PEM-AFC and rank-1 MWF where an M -channel AFC stage is performed first followed by an M -channel NR stage. Although in cascade algorithms where NR is performed first and then AFC the estimation of the feedback path is usually affected by the NR stage, it is shown here that by performing a rank-2 approximation of the speech correlation matrix this issue can be avoided and the feedback path can be correctly estimated. The performance of the algorithms is assessed by means of closed-loop simulations where it is shown that for the considered input signal-to-noise ratios (iSNRs) the cascade $$(M+1)$$ <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:mrow> <mml:mo>(</mml:mo> <mml:mi>M</mml:mi> <mml:mo>+</mml:mo> <mml:mn>1</mml:mn> <mml:mo>)</mml:mo> </mml:mrow> </mml:math> -channel rank-2 MWF and PEM-AFC and the cascade M -channel PEM-AFC and rank-1 MWF algorithms outperform the cascade M -channel rank-1 MWF and PEM-AFC algorithm in terms of the added stable gain (ASG) and misadjustment (Mis) as well as in terms of perceptual metrics such as the short-time objective intelligibility (STOI), perceptual evaluation of speech quality (PESQ), and signal distortion (SD).","PeriodicalId":49309,"journal":{"name":"Journal on Audio Speech and Music Processing","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136155664","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}
Pub Date : 2023-09-20DOI: 10.1186/s13636-023-00298-3
Yicheng Hsu, Mingsian R. Bai
Abstract A three-stage approach is proposed for speaker counting and speech separation in noisy and reverberant environments. In the spatial feature extraction, a spatial coherence matrix (SCM) is computed using whitened relative transfer functions (wRTFs) across time frames. The global activity functions of each speaker are estimated from a simplex constructed using the eigenvectors of the SCM, while the local coherence functions are computed from the coherence between the wRTFs of a time-frequency bin and the global activity function-weighted RTF of the target speaker. In speaker counting, we use the eigenvalues of the SCM and the maximum similarity of the interframe global activity distributions between two speakers as the input features to the speaker counting network (SCnet). In speaker separation, a global and local activity-driven network (GLADnet) is used to extract each independent speaker signal, which is particularly useful for highly overlapping speech signals. Experimental results obtained from the real meeting recordings show that the proposed system achieves superior speaker counting and speaker separation performance compared to previous publications without the prior knowledge of the array configurations.
{"title":"Learning-based robust speaker counting and separation with the aid of spatial coherence","authors":"Yicheng Hsu, Mingsian R. Bai","doi":"10.1186/s13636-023-00298-3","DOIUrl":"https://doi.org/10.1186/s13636-023-00298-3","url":null,"abstract":"Abstract A three-stage approach is proposed for speaker counting and speech separation in noisy and reverberant environments. In the spatial feature extraction, a spatial coherence matrix (SCM) is computed using whitened relative transfer functions (wRTFs) across time frames. The global activity functions of each speaker are estimated from a simplex constructed using the eigenvectors of the SCM, while the local coherence functions are computed from the coherence between the wRTFs of a time-frequency bin and the global activity function-weighted RTF of the target speaker. In speaker counting, we use the eigenvalues of the SCM and the maximum similarity of the interframe global activity distributions between two speakers as the input features to the speaker counting network (SCnet). In speaker separation, a global and local activity-driven network (GLADnet) is used to extract each independent speaker signal, which is particularly useful for highly overlapping speech signals. Experimental results obtained from the real meeting recordings show that the proposed system achieves superior speaker counting and speaker separation performance compared to previous publications without the prior knowledge of the array configurations.","PeriodicalId":49309,"journal":{"name":"Journal on Audio Speech and Music Processing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136263672","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}
Abstract In this paper, we propose a technique for removing a specific type of interference from a monaural recording. Nonstationary interferences are generally challenging to eliminate from such recordings. However, if the interference is a known sound like a cell phone ringtone, music from a CD or streaming service, or a radio or TV broadcast, its source signal can be easily obtained. In our method, we define such interference as an acoustic object. Even if the sampling frequencies of the recording and the acoustic object do not match, we compensate for the mismatch and use the maximum likelihood estimation technique with the auxiliary function to remove the interference from the recording. We compare several probabilistic models for representing the object-canceled signal. Experimental evaluations confirm the effectiveness of our proposed method.
{"title":"Acoustic object canceller: removing a known signal from monaural recording using blind synchronization","authors":"Takao Kawamura, Kouei Yamaoka, Yukoh Wakabayashi, Nobutaka Ono, Ryoichi Miyazaki","doi":"10.1186/s13636-023-00300-y","DOIUrl":"https://doi.org/10.1186/s13636-023-00300-y","url":null,"abstract":"Abstract In this paper, we propose a technique for removing a specific type of interference from a monaural recording. Nonstationary interferences are generally challenging to eliminate from such recordings. However, if the interference is a known sound like a cell phone ringtone, music from a CD or streaming service, or a radio or TV broadcast, its source signal can be easily obtained. In our method, we define such interference as an acoustic object. Even if the sampling frequencies of the recording and the acoustic object do not match, we compensate for the mismatch and use the maximum likelihood estimation technique with the auxiliary function to remove the interference from the recording. We compare several probabilistic models for representing the object-canceled signal. Experimental evaluations confirm the effectiveness of our proposed method.","PeriodicalId":49309,"journal":{"name":"Journal on Audio Speech and Music Processing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135982643","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}
{"title":"The power of humorous audio: exploring emotion regulation in traffic congestion through EEG-based study","authors":"Lekai Zhang, Yingfan Wang, Kailun He, Hailong Zhang, Baixi Xing, Xiaofeng Liu, Fo Hu","doi":"10.1186/s13636-023-00302-w","DOIUrl":"https://doi.org/10.1186/s13636-023-00302-w","url":null,"abstract":"","PeriodicalId":49309,"journal":{"name":"Journal on Audio Speech and Music Processing","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43382828","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}
Pub Date : 2023-09-05DOI: 10.1186/s13636-023-00299-2
Zhiyong Chen, Shugong Xu
{"title":"Learning domain-heterogeneous speaker recognition systems with personalized continual federated learning","authors":"Zhiyong Chen, Shugong Xu","doi":"10.1186/s13636-023-00299-2","DOIUrl":"https://doi.org/10.1186/s13636-023-00299-2","url":null,"abstract":"","PeriodicalId":49309,"journal":{"name":"Journal on Audio Speech and Music Processing","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49629565","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}
Pub Date : 2023-08-25DOI: 10.1186/s13636-023-00297-4
Te Zeng, F. Lau
{"title":"Training audio transformers for cover song identification","authors":"Te Zeng, F. Lau","doi":"10.1186/s13636-023-00297-4","DOIUrl":"https://doi.org/10.1186/s13636-023-00297-4","url":null,"abstract":"","PeriodicalId":49309,"journal":{"name":"Journal on Audio Speech and Music Processing","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44510561","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}
Pub Date : 2023-08-14DOI: 10.1186/s13636-023-00295-6
Shibiao Xu, Zehua Zhang, Mingjiang Wang
{"title":"Channel and temporal-frequency attention UNet for monaural speech enhancement","authors":"Shibiao Xu, Zehua Zhang, Mingjiang Wang","doi":"10.1186/s13636-023-00295-6","DOIUrl":"https://doi.org/10.1186/s13636-023-00295-6","url":null,"abstract":"","PeriodicalId":49309,"journal":{"name":"Journal on Audio Speech and Music Processing","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45794956","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}
Pub Date : 2023-08-08DOI: 10.1186/s13636-023-00301-x
Eric Grinstein, Vincent W. Neo, P. Naylor
{"title":"Dual input neural networks for positional sound source localization","authors":"Eric Grinstein, Vincent W. Neo, P. Naylor","doi":"10.1186/s13636-023-00301-x","DOIUrl":"https://doi.org/10.1186/s13636-023-00301-x","url":null,"abstract":"","PeriodicalId":49309,"journal":{"name":"Journal on Audio Speech and Music Processing","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44921492","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}
Pub Date : 2023-07-01DOI: 10.1186/s13636-023-00293-8
Xingwei Liang, Zehua Zhang, Ruifeng Xu
{"title":"Multi-task deep cross-attention networks for far-field speaker verification and keyword spotting","authors":"Xingwei Liang, Zehua Zhang, Ruifeng Xu","doi":"10.1186/s13636-023-00293-8","DOIUrl":"https://doi.org/10.1186/s13636-023-00293-8","url":null,"abstract":"","PeriodicalId":49309,"journal":{"name":"Journal on Audio Speech and Music Processing","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44852720","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：