Pub Date : 2018-04-26DOI: 10.1109/ICASSP.2018.8462290
Yishan Jiao, Ming Tu, Visar Berisha, J. Liss
Training machine learning algorithms for speech applications requires large, labeled training data sets. This is problematic for clinical applications where obtaining such data is prohibitively expensive because of privacy concerns or lack of access. As a result, clinical speech applications typically rely on small data sets with only tens of speakers. In this paper, we propose a method for simulating training data for clinical applications by transforming healthy speech to dysarthric speech using adversarial training. We evaluate the efficacy of our approach using both objective and subjective criteria. We present the transformed samples to five experienced speech-language pathologists (SLPs) and ask them to identify the samples as healthy or dysarthric. The results reveal that the SLPs identify the transformed speech as dysarthric 65% of the time. In a pilot classification experiment, we show that by using the simulated speech samples to balance an existing dataset, the classification accuracy improves by rv 10% after data augmentation.
{"title":"Simulating Dysarthric Speech for Training Data Augmentation in Clinical Speech Applications","authors":"Yishan Jiao, Ming Tu, Visar Berisha, J. Liss","doi":"10.1109/ICASSP.2018.8462290","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8462290","url":null,"abstract":"Training machine learning algorithms for speech applications requires large, labeled training data sets. This is problematic for clinical applications where obtaining such data is prohibitively expensive because of privacy concerns or lack of access. As a result, clinical speech applications typically rely on small data sets with only tens of speakers. In this paper, we propose a method for simulating training data for clinical applications by transforming healthy speech to dysarthric speech using adversarial training. We evaluate the efficacy of our approach using both objective and subjective criteria. We present the transformed samples to five experienced speech-language pathologists (SLPs) and ask them to identify the samples as healthy or dysarthric. The results reveal that the SLPs identify the transformed speech as dysarthric 65% of the time. In a pilot classification experiment, we show that by using the simulated speech samples to balance an existing dataset, the classification accuracy improves by rv 10% after data augmentation.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"253 1","pages":"6009-6013"},"PeriodicalIF":0.0,"publicationDate":"2018-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77530202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-26DOI: 10.1109/ICASSP.2018.8462318
Jacob Donley, C. Ritz, W. Kleijn
In this paper, we compare the performance of two active dereverberation techniques using a planar array of microphones and loudspeakers. The two techniques are based on a solution to the Kirchhoff-Helmholtz Integral Equation (KHIE). We adapt a Wave Field Synthesis (WFS) based method to the application of real-time 3D dereverberation by using a low-latency pre-filter design. The use of First-Order Differential (FOD) models is also proposed as an alternative method to the use of monopoles with WFS and which does not assume knowledge of the room geometry or primary sources. The two methods are compared by observing the suppression of reflections off a single active wall over the volume of a room in the time and (temporal) frequency domain. The FOD method provides better suppression of reflections than the WFS based method but at the expense of using higher order models. The equivalent absorption coefficients are comparable to passive fibre panel absorbers.
{"title":"On the Comparison of Two Room Compensation / Dereverberation Methods Employing Active Acoustic Boundary Absorption","authors":"Jacob Donley, C. Ritz, W. Kleijn","doi":"10.1109/ICASSP.2018.8462318","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8462318","url":null,"abstract":"In this paper, we compare the performance of two active dereverberation techniques using a planar array of microphones and loudspeakers. The two techniques are based on a solution to the Kirchhoff-Helmholtz Integral Equation (KHIE). We adapt a Wave Field Synthesis (WFS) based method to the application of real-time 3D dereverberation by using a low-latency pre-filter design. The use of First-Order Differential (FOD) models is also proposed as an alternative method to the use of monopoles with WFS and which does not assume knowledge of the room geometry or primary sources. The two methods are compared by observing the suppression of reflections off a single active wall over the volume of a room in the time and (temporal) frequency domain. The FOD method provides better suppression of reflections than the WFS based method but at the expense of using higher order models. The equivalent absorption coefficients are comparable to passive fibre panel absorbers.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"634 1","pages":"221-225"},"PeriodicalIF":0.0,"publicationDate":"2018-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77082801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-25DOI: 10.1109/ICASSP.2018.8462292
Hammad Squalli-Houssaini, Ngoc Q. K. Duong, Gwenaelle Marquant, C. Demarty
Memorability of media content such as images and videos has recently become an important research subject in computer vision. This paper presents our computation model for predicting image memorability, which is based on a deep learning architecture designed for a classification task. We exploit the use of both convolutional neural network (CNN) - based visual features and semantic features related to image captioning for the task. We train and test our model on the large-scale benchmarking memorability dataset: LaMem. Experiment result shows that the proposed computational model obtains better prediction performance than the state of the art, and even outperforms human consistency. We further investigate the genericity of our model on other memorability datasets. Finally, by validating the model on interestingness datasets, we reconfirm the uncorrelation between memorability and interestingness of images.
{"title":"Deep Learning for Predicting Image Memorability","authors":"Hammad Squalli-Houssaini, Ngoc Q. K. Duong, Gwenaelle Marquant, C. Demarty","doi":"10.1109/ICASSP.2018.8462292","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8462292","url":null,"abstract":"Memorability of media content such as images and videos has recently become an important research subject in computer vision. This paper presents our computation model for predicting image memorability, which is based on a deep learning architecture designed for a classification task. We exploit the use of both convolutional neural network (CNN) - based visual features and semantic features related to image captioning for the task. We train and test our model on the large-scale benchmarking memorability dataset: LaMem. Experiment result shows that the proposed computational model obtains better prediction performance than the state of the art, and even outperforms human consistency. We further investigate the genericity of our model on other memorability datasets. Finally, by validating the model on interestingness datasets, we reconfirm the uncorrelation between memorability and interestingness of images.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"118 1","pages":"2371-2375"},"PeriodicalIF":0.0,"publicationDate":"2018-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88038823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-25DOI: 10.1109/ICASSP.2018.8461694
Clément Gaultier, N. Bertin, R. Gribonval
This work features a new algorithm, CASCADE, which leverages a structured cosparse prior across channels to address the multichannel audio declipping problem. CASCADE technique outperforms the state-of-the-art method A-SPADE applied on each channel separately in all tested settings, while retaining similar runtime.
{"title":"Cascade: Channel-Aware Structured Cosparse Audio Declipper","authors":"Clément Gaultier, N. Bertin, R. Gribonval","doi":"10.1109/ICASSP.2018.8461694","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8461694","url":null,"abstract":"This work features a new algorithm, CASCADE, which leverages a structured cosparse prior across channels to address the multichannel audio declipping problem. CASCADE technique outperforms the state-of-the-art method A-SPADE applied on each channel separately in all tested settings, while retaining similar runtime.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"19 1","pages":"571-575"},"PeriodicalIF":0.0,"publicationDate":"2018-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91157816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-25DOI: 10.1109/ICASSP.2018.8461476
Guillaume Carbajal, R. Serizel, E. Vincent, E. Humbert
A residual echo suppressor (RES) aims to suppress the residual echo in the output of an acoustic echo canceler (AEC). Spectral-based RES approaches typically estimate the magnitude spectra of the near-end speech and the residual echo from a single input, that is either the far-end speech or the echo computed by the AEC, and derive the RES filter coefficients accordingly. These single inputs do not always suffice to discriminate the near-end speech from the remaining echo. In this paper, we propose a neural network-based approach that directly estimates the RES filter coefficients from multiple inputs, including the AEC output, the far-end speech, and/or the echo computed by the AEC. We evaluate our system on real recordings of acoustic echo and near-end speech acquired in various situations with a smart speaker. We compare it to two single-input spectral-based approaches in terms of echo reduction and near-end speech distortion.
{"title":"Multiple-Input Neural Network-Based Residual Echo Suppression","authors":"Guillaume Carbajal, R. Serizel, E. Vincent, E. Humbert","doi":"10.1109/ICASSP.2018.8461476","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8461476","url":null,"abstract":"A residual echo suppressor (RES) aims to suppress the residual echo in the output of an acoustic echo canceler (AEC). Spectral-based RES approaches typically estimate the magnitude spectra of the near-end speech and the residual echo from a single input, that is either the far-end speech or the echo computed by the AEC, and derive the RES filter coefficients accordingly. These single inputs do not always suffice to discriminate the near-end speech from the remaining echo. In this paper, we propose a neural network-based approach that directly estimates the RES filter coefficients from multiple inputs, including the AEC output, the far-end speech, and/or the echo computed by the AEC. We evaluate our system on real recordings of acoustic echo and near-end speech acquired in various situations with a smart speaker. We compare it to two single-input spectral-based approaches in terms of echo reduction and near-end speech distortion.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"68 1","pages":"231-235"},"PeriodicalIF":0.0,"publicationDate":"2018-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90500564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-25DOI: 10.1109/ICASSP.2018.8461423
Qing Wang, Wei Rao, Sining Sun, Lei Xie, Chng Eng Siong, Haizhou Li
The i-vector approach to speaker recognition has achieved good performance when the domain of the evaluation dataset is similar to that of the training dataset. However, in realworld applications, there is always a mismatch between the training and evaluation datasets, that leads to performance degradation. To address this problem, this paper proposes to learn the domain-invariant and speaker-discriminative speech representations via domain adversarial training. Specifically, with domain adversarial training method, we use a gradient reversal layer to remove the domain variation and project the different domain data into the same subspace. Moreover, we compare the proposed method with other state-of-the-art unsupervised domain adaptation techniques for i-vector approach to speaker recognition (e.g. autoencoder based domain adaptation, inter dataset variability compensation, dataset-invariant covariance normalization, and so on). Experiments on 2013 domain adaptation challenge (DAC) dataset demonstrate that the proposed method is not only effective in solving the dataset mismatch problem, but also outperforms the compared unsupervised domain adaptation methods.
{"title":"Unsupervised Domain Adaptation via Domain Adversarial Training for Speaker Recognition","authors":"Qing Wang, Wei Rao, Sining Sun, Lei Xie, Chng Eng Siong, Haizhou Li","doi":"10.1109/ICASSP.2018.8461423","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8461423","url":null,"abstract":"The i-vector approach to speaker recognition has achieved good performance when the domain of the evaluation dataset is similar to that of the training dataset. However, in realworld applications, there is always a mismatch between the training and evaluation datasets, that leads to performance degradation. To address this problem, this paper proposes to learn the domain-invariant and speaker-discriminative speech representations via domain adversarial training. Specifically, with domain adversarial training method, we use a gradient reversal layer to remove the domain variation and project the different domain data into the same subspace. Moreover, we compare the proposed method with other state-of-the-art unsupervised domain adaptation techniques for i-vector approach to speaker recognition (e.g. autoencoder based domain adaptation, inter dataset variability compensation, dataset-invariant covariance normalization, and so on). Experiments on 2013 domain adaptation challenge (DAC) dataset demonstrate that the proposed method is not only effective in solving the dataset mismatch problem, but also outperforms the compared unsupervised domain adaptation methods.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"1993 1","pages":"4889-4893"},"PeriodicalIF":0.0,"publicationDate":"2018-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82398805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-25DOI: 10.1109/ICASSP.2018.8461842
Anh T. Pham, R. Raich, Xiaoli Z. Fern
Clustering is widely used for exploratory data analysis in a variety of applications. Traditionally clustering is studied as an unsupervised task where no human inputs are provided. A recent trend in clustering is to leverage user provided side information to better infer the clustering structure in data. In this paper, we propose a probabilistic graphical model that allows user to provide as input the desired cluster sizes, namely the cardinality constraints. Our model also incorporates a flexible mechanism to inject control of the crispness of the clusters. Experiments on synthetic and real data demonstrate the effectiveness of the proposed method in learning with cardinality constraints in comparison with the current state-of-the-art.
{"title":"Discriminative Clustering with Cardinality Constraints","authors":"Anh T. Pham, R. Raich, Xiaoli Z. Fern","doi":"10.1109/ICASSP.2018.8461842","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8461842","url":null,"abstract":"Clustering is widely used for exploratory data analysis in a variety of applications. Traditionally clustering is studied as an unsupervised task where no human inputs are provided. A recent trend in clustering is to leverage user provided side information to better infer the clustering structure in data. In this paper, we propose a probabilistic graphical model that allows user to provide as input the desired cluster sizes, namely the cardinality constraints. Our model also incorporates a flexible mechanism to inject control of the crispness of the clusters. Experiments on synthetic and real data demonstrate the effectiveness of the proposed method in learning with cardinality constraints in comparison with the current state-of-the-art.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"232 1","pages":"2291-2295"},"PeriodicalIF":0.0,"publicationDate":"2018-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75893675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-25DOI: 10.1109/ICASSP.2018.8462566
Kriti Kumar, A. Majumdar, M. G. Chandra, A. A. Kumar
In this paper, we present a kernelized dictionary learning framework for carrying out regression to model signals having a complex nonlinear nature. A joint optimization is carried out where the regression weights are learnt together with the dictionary and coefficients. Relevant formulation and dictionary building steps are provided. To demonstrate the effectiveness of the proposed technique, elaborate experimental results using different real-life datasets are presented. The results show that non-linear dictionary is more accurate for data modeling and provides significant improvement in estimation accuracy over the other popular traditional techniques especially when the data is highly non-linear.
{"title":"Regressing Kernel Dictionary Learning","authors":"Kriti Kumar, A. Majumdar, M. G. Chandra, A. A. Kumar","doi":"10.1109/ICASSP.2018.8462566","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8462566","url":null,"abstract":"In this paper, we present a kernelized dictionary learning framework for carrying out regression to model signals having a complex nonlinear nature. A joint optimization is carried out where the regression weights are learnt together with the dictionary and coefficients. Relevant formulation and dictionary building steps are provided. To demonstrate the effectiveness of the proposed technique, elaborate experimental results using different real-life datasets are presented. The results show that non-linear dictionary is more accurate for data modeling and provides significant improvement in estimation accuracy over the other popular traditional techniques especially when the data is highly non-linear.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"10 1","pages":"2756-2760"},"PeriodicalIF":0.0,"publicationDate":"2018-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88722111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-25DOI: 10.1109/ICASSP.2018.8462099
Anh T. Pham, R. Raich, Xiaoli Z. Fern, Weng-Keen Wong, Xinze Guan
Multiple-instance learning is a framework for learning from data consisting of bags of instances labeled at the bag level. A common assumption in multi-instance learning is that a bag label is positive if and only if at least one instance in the bag is positive. In practice, this assumption may be violated. For example, experts may provide a noisy label to a bag consisting of many instances, to reduce labeling time. Here, we consider generalized multi-instance learning, which assumes that the bag label is non-deterministically determined based on the number of positive instances in the bag. The challenge in this setting is to simultaneous learn an instance classifier and the unknown bag-labeling probabilistic rule. This paper addresses the generalized multi-instance learning using a discriminative probabilistic graphical model with exact and efficient inference. Experiments on both synthetic and real data illustrate the effectiveness of the proposed method relative to other methods including those that follow the traditional multiple-instance learning assumption.
{"title":"Discriminative Probabilistic Framework for Generalized Multi-Instance Learning","authors":"Anh T. Pham, R. Raich, Xiaoli Z. Fern, Weng-Keen Wong, Xinze Guan","doi":"10.1109/ICASSP.2018.8462099","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8462099","url":null,"abstract":"Multiple-instance learning is a framework for learning from data consisting of bags of instances labeled at the bag level. A common assumption in multi-instance learning is that a bag label is positive if and only if at least one instance in the bag is positive. In practice, this assumption may be violated. For example, experts may provide a noisy label to a bag consisting of many instances, to reduce labeling time. Here, we consider generalized multi-instance learning, which assumes that the bag label is non-deterministically determined based on the number of positive instances in the bag. The challenge in this setting is to simultaneous learn an instance classifier and the unknown bag-labeling probabilistic rule. This paper addresses the generalized multi-instance learning using a discriminative probabilistic graphical model with exact and efficient inference. Experiments on both synthetic and real data illustrate the effectiveness of the proposed method relative to other methods including those that follow the traditional multiple-instance learning assumption.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"18 1","pages":"2281-2285"},"PeriodicalIF":0.0,"publicationDate":"2018-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84817979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-24DOI: 10.1109/ICASSP.2018.8461519
Fabrice Katzberg, Radoslaw Mazur, M. Maass, P. Koch, A. Mertins
For conventional sampling of sound-fields, the measurement in space by use of stationary microphones is impractical for high audio frequencies. Satisfying the Nyquist-Shannon sampling theorem requires a huge number of sampling points and entails other difficulties, such as the need for exact calibration and spatial positioning of a large number of microphones. Dynamic sound-field measurements involving tracked microphones may weaken this spatial sampling problem. However, for aliasing-free reconstruction, there is still the need of sampling a huge number of unknown sound-field variables. Thus in real-world applications, the trajectories may be expected to lead to underdetermined sampling problems. In this paper, we present a compressed sensing framework that allows for stable and robust sub-Nyquist sampling of sound fields by use of moving microphones.
{"title":"Compressive Sampling of Sound Fields Using Moving Microphones","authors":"Fabrice Katzberg, Radoslaw Mazur, M. Maass, P. Koch, A. Mertins","doi":"10.1109/ICASSP.2018.8461519","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8461519","url":null,"abstract":"For conventional sampling of sound-fields, the measurement in space by use of stationary microphones is impractical for high audio frequencies. Satisfying the Nyquist-Shannon sampling theorem requires a huge number of sampling points and entails other difficulties, such as the need for exact calibration and spatial positioning of a large number of microphones. Dynamic sound-field measurements involving tracked microphones may weaken this spatial sampling problem. However, for aliasing-free reconstruction, there is still the need of sampling a huge number of unknown sound-field variables. Thus in real-world applications, the trajectories may be expected to lead to underdetermined sampling problems. In this paper, we present a compressed sensing framework that allows for stable and robust sub-Nyquist sampling of sound fields by use of moving microphones.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"85 1","pages":"181-185"},"PeriodicalIF":0.0,"publicationDate":"2018-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85483167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：