2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)最新文献_第9页

Complex spectrogram enhancement by convolutional neural network with multi-metrics learning 基于多指标学习的卷积神经网络复谱图增强

2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2017-04-27 DOI: 10.1109/MLSP.2017.8168119

Szu-Wei Fu, Ting-yao Hu, Yu Tsao, Xugang Lu

{"title":"Complex spectrogram enhancement by convolutional neural network with multi-metrics learning","authors":"Szu-Wei Fu, Ting-yao Hu, Yu Tsao, Xugang Lu","doi":"10.1109/MLSP.2017.8168119","DOIUrl":"https://doi.org/10.1109/MLSP.2017.8168119","url":null,"abstract":"This paper aims to address two issues existing in the current speech enhancement methods: 1) the difficulty of phase estimations; 2) a single objective function cannot consider multiple metrics simultaneously. To solve the first problem, we propose a novel convolutional neural network (CNN) model for complex spectrogram enhancement, namely estimating clean real and imaginary (RI) spectrograms from noisy ones. The reconstructed RI spectrograms are directly used to synthesize enhanced speech waveforms. In addition, since log-power spectrogram (LPS) can be represented as a function of RI spectrograms, its reconstruction is also considered as another target. Thus a unified objective function, which combines these two targets (reconstruction of RI spectrograms and LPS), is equivalent to simultaneously optimizing two commonly used objective metrics: segmental signal-to-noise ratio (SSNR) and log-spectral distortion (LSD). Therefore, the learning process is called multi-metrics learning (MML). Experimental results confirm the effectiveness of the proposed CNN with RI spectrograms and MML in terms of improved standardized evaluation metrics on a speech enhancement task.","PeriodicalId":6542,"journal":{"name":"2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"141 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80109280","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}

引用次数: 151

Scene-Adapted plug-and-play algorithm with convergence guarantees 具有收敛保证的场景适应即插即用算法

2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2017-02-08 DOI: 10.1109/MLSP.2017.8168194

Afonso M. Teodoro, J. Bioucas-Dias, Mário A. T. Figueiredo

引用次数: 29

Multi-Objective contextual bandits with a dominant objective 具有主导目标的多目标情境强盗

2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2017-01-01 DOI: 10.1109/MLSP.2017.8168123

Cem Tekin, E. Turğay

{"title":"Multi-Objective contextual bandits with a dominant objective","authors":"Cem Tekin, E. Turğay","doi":"10.1109/MLSP.2017.8168123","DOIUrl":"https://doi.org/10.1109/MLSP.2017.8168123","url":null,"abstract":"In this paper, we propose a new contextual bandit problem with two objectives, where one of the objectives dominates the other objective. Unlike single-objective bandit problems in which the learner obtains a random scalar reward for each arm it selects, in the proposed problem, the learner obtains a random reward vector, where each component of the reward vector corresponds to one of the objectives. The goal of the learner is to maximize its total reward in the non-dominant objective while ensuring that it maximizes its reward in the dominant objective. In this case, the optimal arm given a context is the one that maximizes the expected reward in the non-dominant objective among all arms that maximize the expected reward in the dominant objective. For this problem, we propose the multi-objective contextual multi-armed bandit algorithm (MOC-MAB), and prove that it achieves sublinear regret with respect to the optimal context dependent policy. Then, we compare the performance of the proposed algorithm with other state-of-the-art bandit algorithms. The proposed contextual bandit model and the algorithm have a wide range of real-world applications that involve multiple and possibly conflicting objectives ranging from wireless communication to medical diagnosis and recommender systems.","PeriodicalId":6542,"journal":{"name":"2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"110 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76066702","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}

引用次数: 9

Learning guided convolutional neural networks for cross-resolution face recognition 学习引导卷积神经网络用于交叉分辨率人脸识别

2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2017-01-01 DOI: 10.1109/MLSP.2017.8168180

Tzu-Chien Fu, Wei-Chen Chiu, Y. Wang

引用次数: 13

Domain-Adaptive generative adversarial networks for sketch-to-photo inversion 领域自适应生成对抗网络用于草图到照片的反演

2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2017-01-01 DOI: 10.1109/MLSP.2017.8168181

Yen-Cheng Liu, Wei-Chen Chiu, Sheng-De Wang, Y. Wang

引用次数: 7

Adversarial domain separation and adaptation 对抗性领域分离和适应

2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2017-01-01 DOI: 10.1109/MLSP.2017.8168121

Jen-Chieh Tsai, Jen-Tzung Chien

引用次数: 18

Iterative data-driven coronary vessel labeling 迭代数据驱动的冠状血管标记

2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2017-01-01 DOI: 10.1109/MLSP.2017.8168190

Tsaipei Wang

引用次数: 0

Memory augmented neural network for source separation 用于源分离的记忆增强神经网络

2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2017-01-01 DOI: 10.1109/MLSP.2017.8168120

K. Tsou, Jen-Tzung Chien

引用次数: 11

End-to-End learning of cost-volume aggregation for real-time dense stereo 实时密集立体系统中成本-体积聚合的端到端学习

2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2016-11-17 DOI: 10.1109/MLSP.2017.8168183

Andrey Kuzmin, Dmitry Mikushin, V. Lempitsky

引用次数: 26

Parallelizable sparse inverse formulation Gaussian processes (SpInGP) 并行稀疏逆公式高斯过程(SpInGP)

2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2016-10-25 DOI: 10.1109/MLSP.2017.8168130

A. Grigorievskiy, Neil D. Lawrence, S. Särkkä

引用次数: 20