Pub Date : 2017-06-19DOI: 10.1109/ICASSP.2017.7952172
Filip Elvander, Stefan Ingi Adalbjornsson, J. Karlsson, A. Jakobsson
In this work, we propose a novel multi-pitch estimation technique that is robust with respect to the inharmonicity commonly occurring in many applications. The method does not require any a priori knowledge of the number of signal sources, the number of harmonics of each source, nor the structure or scope of any possibly occurring inharmonicity. Formulated as a minimum transport distance problem, the proposed method finds an estimate of the present pitches by mapping any found spectral line to the closest harmonic structure. The resulting optimization is a convex and highly tractable linear programming problem. The preferable performance of the proposed method is illustrated using both simulated and real audio signals.
{"title":"Using optimal transport for estimating inharmonic pitch signals","authors":"Filip Elvander, Stefan Ingi Adalbjornsson, J. Karlsson, A. Jakobsson","doi":"10.1109/ICASSP.2017.7952172","DOIUrl":"https://doi.org/10.1109/ICASSP.2017.7952172","url":null,"abstract":"In this work, we propose a novel multi-pitch estimation technique that is robust with respect to the inharmonicity commonly occurring in many applications. The method does not require any a priori knowledge of the number of signal sources, the number of harmonics of each source, nor the structure or scope of any possibly occurring inharmonicity. Formulated as a minimum transport distance problem, the proposed method finds an estimate of the present pitches by mapping any found spectral line to the closest harmonic structure. The resulting optimization is a convex and highly tractable linear programming problem. The preferable performance of the proposed method is illustrated using both simulated and real audio signals.","PeriodicalId":118243,"journal":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125633376","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 : 2017-06-19DOI: 10.1109/ICASSP.2017.7953087
Xin Wang, Shinji Takaki, J. Yamagishi
Neural-network-based generative models, such as mixture density networks, are potential solutions for speech synthesis. In this paper we follow this path and propose a recurrent mixture density network that incorporates a trainable autoregressive model. An advantage of incorporating an autoregressive model is that the time dependency within acoustic feature trajectories can be modeled without using the conventional dynamic features. More interestingly, experiments show that this autoregressive model learns to be a filter that emphasizes the high frequency components of the target acoustic feature trajectories in the training stage. In the synthesis stage, it boosts the low frequency components of the generated feature trajectories and hence increases their global variance. Experimental results show that the proposed model achieved higher likelihood on the training data and generated speech with better quality than other models when dynamic features were not utilized in any model.
{"title":"An autoregressive recurrent mixture density network for parametric speech synthesis","authors":"Xin Wang, Shinji Takaki, J. Yamagishi","doi":"10.1109/ICASSP.2017.7953087","DOIUrl":"https://doi.org/10.1109/ICASSP.2017.7953087","url":null,"abstract":"Neural-network-based generative models, such as mixture density networks, are potential solutions for speech synthesis. In this paper we follow this path and propose a recurrent mixture density network that incorporates a trainable autoregressive model. An advantage of incorporating an autoregressive model is that the time dependency within acoustic feature trajectories can be modeled without using the conventional dynamic features. More interestingly, experiments show that this autoregressive model learns to be a filter that emphasizes the high frequency components of the target acoustic feature trajectories in the training stage. In the synthesis stage, it boosts the low frequency components of the generated feature trajectories and hence increases their global variance. Experimental results show that the proposed model achieved higher likelihood on the training data and generated speech with better quality than other models when dynamic features were not utilized in any model.","PeriodicalId":118243,"journal":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"312 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124439721","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 : 2017-06-19DOI: 10.1109/ICASSP.2017.7952340
Stephen Laide, J. McAllister
The increasing pervasion and scale of machine learning technologies is posing fundamental challenges for their realisation. In the main, current algorithms are centralised, with a large number of processing agents, distributed across parallel processing resources, accessing a single, very large data object. This creates bottlenecks as a result of limited memory access rates. Distributed learning has the potential to resolve this problem by employing networks of co-operating agents each operating on subsets of the data, but as yet their suitability for realisation on parallel architectures such as multicore are unknown. This paper presents the results of a case study deploying distributed dictionary learning for microarray gene expression bi-clustering on a 16-core Epiphany multicore. It shows that distributed learning approaches can enable near-linear speed-up with the number of processing resources and, via the use of DMA-based communication, a 50% increase in throughput can be enabled.
{"title":"Multicore distributed dictionary learning: A microarray gene expression biclustering case study","authors":"Stephen Laide, J. McAllister","doi":"10.1109/ICASSP.2017.7952340","DOIUrl":"https://doi.org/10.1109/ICASSP.2017.7952340","url":null,"abstract":"The increasing pervasion and scale of machine learning technologies is posing fundamental challenges for their realisation. In the main, current algorithms are centralised, with a large number of processing agents, distributed across parallel processing resources, accessing a single, very large data object. This creates bottlenecks as a result of limited memory access rates. Distributed learning has the potential to resolve this problem by employing networks of co-operating agents each operating on subsets of the data, but as yet their suitability for realisation on parallel architectures such as multicore are unknown. This paper presents the results of a case study deploying distributed dictionary learning for microarray gene expression bi-clustering on a 16-core Epiphany multicore. It shows that distributed learning approaches can enable near-linear speed-up with the number of processing resources and, via the use of DMA-based communication, a 50% increase in throughput can be enabled.","PeriodicalId":118243,"journal":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116903305","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 : 2017-06-16DOI: 10.1109/ICASSP.2017.7952543
H. Ahmed, M. Wong, A. Nandi
Owing to the importance of rolling element bearings in rotating machines, condition monitoring of rolling element bearings has been studied extensively over the past decades. However, most of the existing techniques require large storage and time for signal processing. This paper presents a new strategy based on compressive sensing for bearing faults classification that uses fewer measurements. Under this strategy, to match the compressed sensing mechanism, the compressed vibration signals are first obtained by resampling the acquired bearing vibration signals in the time domain with a random Gaussian matrix using different compressed sensing sampling rates. Then three approaches have been chosen to process these compressed data for the purpose of bearing fault classification these includes using the data directly as the input of classifier, and extract features from the data using linear feature extraction methods, namely, unsupervised Principal Component Analysis (PCA) and supervised Linear Discriminant Analysis (LDA). Classification performance using Logistic Regression Classifier (LRC) achieved high classification accuracy with significantly reduced bandwidth consumption compared with the existing techniques.
{"title":"Compressive sensing strategy for classification of bearing faults","authors":"H. Ahmed, M. Wong, A. Nandi","doi":"10.1109/ICASSP.2017.7952543","DOIUrl":"https://doi.org/10.1109/ICASSP.2017.7952543","url":null,"abstract":"Owing to the importance of rolling element bearings in rotating machines, condition monitoring of rolling element bearings has been studied extensively over the past decades. However, most of the existing techniques require large storage and time for signal processing. This paper presents a new strategy based on compressive sensing for bearing faults classification that uses fewer measurements. Under this strategy, to match the compressed sensing mechanism, the compressed vibration signals are first obtained by resampling the acquired bearing vibration signals in the time domain with a random Gaussian matrix using different compressed sensing sampling rates. Then three approaches have been chosen to process these compressed data for the purpose of bearing fault classification these includes using the data directly as the input of classifier, and extract features from the data using linear feature extraction methods, namely, unsupervised Principal Component Analysis (PCA) and supervised Linear Discriminant Analysis (LDA). Classification performance using Logistic Regression Classifier (LRC) achieved high classification accuracy with significantly reduced bandwidth consumption compared with the existing techniques.","PeriodicalId":118243,"journal":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122428101","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 : 2017-06-16DOI: 10.1109/ICASSP.2017.7952568
Asahi Ushio, M. Yukawa
We present a variant of the regularized dual averaging (RDA) algorithm for stochastic sparse optimization. Our approach differs from the previous studies of RDA in two respects. First, a sparsity-promoting metric is employed, originated from the proportionate-type adaptive filtering algorithms. Second, the squared-distance function to a closed convex set is employed as a part of the objective functions. In the particular application of online regression, the squared-distance function is reduced to a normalized version of the typical squared-error (least square) function. The two differences yield a better sparsity-seeking capability, leading to improved convergence properties. Numerical examples show the advantages of the proposed algorithm over the existing methods including ADAGRAD and adaptive proximal forward-backward splitting (APFBS).
{"title":"Projection-based dual averaging for stochastic sparse optimization","authors":"Asahi Ushio, M. Yukawa","doi":"10.1109/ICASSP.2017.7952568","DOIUrl":"https://doi.org/10.1109/ICASSP.2017.7952568","url":null,"abstract":"We present a variant of the regularized dual averaging (RDA) algorithm for stochastic sparse optimization. Our approach differs from the previous studies of RDA in two respects. First, a sparsity-promoting metric is employed, originated from the proportionate-type adaptive filtering algorithms. Second, the squared-distance function to a closed convex set is employed as a part of the objective functions. In the particular application of online regression, the squared-distance function is reduced to a normalized version of the typical squared-error (least square) function. The two differences yield a better sparsity-seeking capability, leading to improved convergence properties. Numerical examples show the advantages of the proposed algorithm over the existing methods including ADAGRAD and adaptive proximal forward-backward splitting (APFBS).","PeriodicalId":118243,"journal":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122284998","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 : 2017-06-16DOI: 10.1109/ICASSP.2017.7952745
T. Tachikawa, K. Yatabe, Yasuhiro Oikawa
In this paper, 3D sound source localization method for simultaneously estimating both direction-of-arrival (DOA) and distance from the microphone array is proposed. For estimating distance, the off-grid problem must be overcome because the range of distance to be considered is quite broad and even not bounded. The proposed method estimates positions based on an extension of the convex clustering method combined with sparse coefficients estimation. A method for constructing a suitable monopole dictionary based on coherence is also proposed so that the convex clustering based method appropriately estimate distance of sound sources. Numerical experiments of distance estimation and 3D localization show possibility of the proposed method.
{"title":"Coherence-adjusted monopole dictionary and convex clustering for 3D localization of mixed near-field and far-field sources","authors":"T. Tachikawa, K. Yatabe, Yasuhiro Oikawa","doi":"10.1109/ICASSP.2017.7952745","DOIUrl":"https://doi.org/10.1109/ICASSP.2017.7952745","url":null,"abstract":"In this paper, 3D sound source localization method for simultaneously estimating both direction-of-arrival (DOA) and distance from the microphone array is proposed. For estimating distance, the off-grid problem must be overcome because the range of distance to be considered is quite broad and even not bounded. The proposed method estimates positions based on an extension of the convex clustering method combined with sparse coefficients estimation. A method for constructing a suitable monopole dictionary based on coherence is also proposed so that the convex clustering based method appropriately estimate distance of sound sources. Numerical experiments of distance estimation and 3D localization show possibility of the proposed method.","PeriodicalId":118243,"journal":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130791318","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 : 2017-06-16DOI: 10.1109/ICASSP.2017.7953096
Ana Ramírez López, R. Saeidi, Lauri Juvela, P. Alku
Speaker recognition performance degrades substantially in case of vocal effort mismatch (e.g. shouted vs. normal speech) between test and enrollment utterances. Such a mismatch is often encountered, for example, in forensic speaker recognition. This paper introduces a novel spectral mapping method which, when employed jointly with a statistical mapping technique, converts the Mel-frequency band energies of normal speech towards their counterparts in shouted speech. The aim is to obtain more robust performance in speaker recognition by tackling vocal effort mismatch between enrollment and test utterances. The processing is performed on the speech signal before feature extraction. The proposed approach was evaluated by testing the performance of a state-of-the-art i-vector-based speaker recognition system with and without applying the spectral mapping processing to the enrollment data. The results show that pre-processing with the proposed approach results in considerable improvement in correct identification rates.
{"title":"Normal-to-shouted speech spectral mapping for speaker recognition under vocal effort mismatch","authors":"Ana Ramírez López, R. Saeidi, Lauri Juvela, P. Alku","doi":"10.1109/ICASSP.2017.7953096","DOIUrl":"https://doi.org/10.1109/ICASSP.2017.7953096","url":null,"abstract":"Speaker recognition performance degrades substantially in case of vocal effort mismatch (e.g. shouted vs. normal speech) between test and enrollment utterances. Such a mismatch is often encountered, for example, in forensic speaker recognition. This paper introduces a novel spectral mapping method which, when employed jointly with a statistical mapping technique, converts the Mel-frequency band energies of normal speech towards their counterparts in shouted speech. The aim is to obtain more robust performance in speaker recognition by tackling vocal effort mismatch between enrollment and test utterances. The processing is performed on the speech signal before feature extraction. The proposed approach was evaluated by testing the performance of a state-of-the-art i-vector-based speaker recognition system with and without applying the spectral mapping processing to the enrollment data. The results show that pre-processing with the proposed approach results in considerable improvement in correct identification rates.","PeriodicalId":118243,"journal":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133388889","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 : 2017-06-16DOI: 10.1109/ICASSP.2017.7952799
Karthik Upadhya, S. Vorobyov, Mikko Vehkaperä
In massive multiple-input multiple-output (MIMO) systems, superimposed (SP) and time-multiplexed (TM) pilots exhibit a complementary behavior, with the former and latter schemes offering a higher throughput in high and low inter-cell interference scenarios, respectively. Based on this observation, in this paper, we propose an algorithm for partitioning users into two disjoint sets comprising users that transmit TM and SP pilots. This selection of user sets is accomplished by minimizing the total inter-cell and intra-cell interference, and since this problem is found to be non-convex, a greedy approach is proposed to perform the partitioning. Based on simulations, it is shown that the proposed method is versatile and offers an improved performance in both high and low-interference scenarios.
{"title":"Time-multiplexed / superimposed pilot selection for massive MIMO pilot decontamination","authors":"Karthik Upadhya, S. Vorobyov, Mikko Vehkaperä","doi":"10.1109/ICASSP.2017.7952799","DOIUrl":"https://doi.org/10.1109/ICASSP.2017.7952799","url":null,"abstract":"In massive multiple-input multiple-output (MIMO) systems, superimposed (SP) and time-multiplexed (TM) pilots exhibit a complementary behavior, with the former and latter schemes offering a higher throughput in high and low inter-cell interference scenarios, respectively. Based on this observation, in this paper, we propose an algorithm for partitioning users into two disjoint sets comprising users that transmit TM and SP pilots. This selection of user sets is accomplished by minimizing the total inter-cell and intra-cell interference, and since this problem is found to be non-convex, a greedy approach is proposed to perform the partitioning. Based on simulations, it is shown that the proposed method is versatile and offers an improved performance in both high and low-interference scenarios.","PeriodicalId":118243,"journal":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124802355","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 : 2017-06-16DOI: 10.1109/ICASSP.2017.7952444
Yao-Jen Chang, Pei-Hsuan Tsai, Chun-Lung Lin
To realize the medical video applications, this paper proposes several lossless compression methods over high efficiency video coding (HEVC). A generalized intra block copy (GIBC) is first proposed to predict the coding unit by a reference block, whose samples could be fully or partially reconstructed. A cyclic block padding technique is also proposed to predict the unreconstructed samples in the reference block by geometrically co-located blocks. Based on the feature distribution analyses for palette coding, we further propose an HEVC-based medical video coder (HMC), which combines the GIBC, line-coded palette coding and intra palette predictor without mutual conflicts. Experimental results show that, compared to the lossless HEVC, the proposed GIBC and HMC respectively save up to 13.9% and 22.3% bits over medical videos.
{"title":"Novel medical video compression methods over lossless HEVC coder","authors":"Yao-Jen Chang, Pei-Hsuan Tsai, Chun-Lung Lin","doi":"10.1109/ICASSP.2017.7952444","DOIUrl":"https://doi.org/10.1109/ICASSP.2017.7952444","url":null,"abstract":"To realize the medical video applications, this paper proposes several lossless compression methods over high efficiency video coding (HEVC). A generalized intra block copy (GIBC) is first proposed to predict the coding unit by a reference block, whose samples could be fully or partially reconstructed. A cyclic block padding technique is also proposed to predict the unreconstructed samples in the reference block by geometrically co-located blocks. Based on the feature distribution analyses for palette coding, we further propose an HEVC-based medical video coder (HMC), which combines the GIBC, line-coded palette coding and intra palette predictor without mutual conflicts. Experimental results show that, compared to the lossless HEVC, the proposed GIBC and HMC respectively save up to 13.9% and 22.3% bits over medical videos.","PeriodicalId":118243,"journal":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127612779","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 : 2017-06-16DOI: 10.1109/ICASSP.2017.7952658
Po-Yuan Shih, Chia-Ping Chen, Chung-Hsien Wu
In this paper, we propose to apply ensemble learning methods on neural networks to improve the performance of speech emotion recognition tasks. The basic idea is to first divide unbalanced data set into balanced subsets and then combine the predictions of the models trained on these subsets. Several methods regarding the decomposition of data and the exploitation of model predictions are investigated in this study. On the public-domain FAU-Aibo database, which is used in Interspeech Emotion Challenge evaluation, the best performance we achieve is an unweighted average (UA) recall rate of 45.5% for the 5-class classification task. Furthermore, such performance is achieved with a feature space of 40-dimension. Compared to the baseline system with 384-dimension feature vector per example and an UA of 38.9%, such a performance is very impressive. Indeed, this is one of the best performances on FAU-Aibo within the static modeling framework.
{"title":"Speech emotion recognition with ensemble learning methods","authors":"Po-Yuan Shih, Chia-Ping Chen, Chung-Hsien Wu","doi":"10.1109/ICASSP.2017.7952658","DOIUrl":"https://doi.org/10.1109/ICASSP.2017.7952658","url":null,"abstract":"In this paper, we propose to apply ensemble learning methods on neural networks to improve the performance of speech emotion recognition tasks. The basic idea is to first divide unbalanced data set into balanced subsets and then combine the predictions of the models trained on these subsets. Several methods regarding the decomposition of data and the exploitation of model predictions are investigated in this study. On the public-domain FAU-Aibo database, which is used in Interspeech Emotion Challenge evaluation, the best performance we achieve is an unweighted average (UA) recall rate of 45.5% for the 5-class classification task. Furthermore, such performance is achieved with a feature space of 40-dimension. Compared to the baseline system with 384-dimension feature vector per example and an UA of 38.9%, such a performance is very impressive. Indeed, this is one of the best performances on FAU-Aibo within the static modeling framework.","PeriodicalId":118243,"journal":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125919604","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：