2020 International Conference on Signal Processing and Communications (SPCOM)最新文献_第6页

Intelligibility Improvement of Dysarthric Speech using MMSE DiscoGAN 使用MMSE DiscoGAN改善困难言语的可理解性

2020 International Conference on Signal Processing and Communications (SPCOM) Pub Date : 2020-07-01 DOI: 10.1109/SPCOM50965.2020.9179511

Mirali Purohit, Maitreya Patel, Harshit Malaviya, Ankur T. Patil, Mihir Parmar, Nirmesh J. Shah, Savan Doshi, H. Patil

{"title":"Intelligibility Improvement of Dysarthric Speech using MMSE DiscoGAN","authors":"Mirali Purohit, Maitreya Patel, Harshit Malaviya, Ankur T. Patil, Mihir Parmar, Nirmesh J. Shah, Savan Doshi, H. Patil","doi":"10.1109/SPCOM50965.2020.9179511","DOIUrl":"https://doi.org/10.1109/SPCOM50965.2020.9179511","url":null,"abstract":"Dysarthria is a manifestation of the disordering in articulatory parts that are used during speech production, which results in uneven, slow, slurred, monotone speech or speech in an abnormal rhythm. People with dysarthria produce less intelligible speech. Improving the intelligibility of dysarthric speech is challenging because unlike normal speech, there is less amount of data for dysarthric speech. It is a known fact that dysarthric speech and normal speech are different in speech production-perception perspectives. Recently, Generative Adversarial Network (GAN)-based architectures have become more popular to learn such kind of cross-domain relationships efficiently. In this paper, we propose to use Discover GAN (DiscoGAN) along with Mean Square Error (MSE) regularization (i.e., MMSE DiscoGAN) for Dysarthric-to-Normal speech conversion. In particular, a direct feature-based mapping technique is used to train all the models. In the end, we use the Automatic Speech Recognition (ASR) to measure the Phoneme Error Rate (PER) for a particular speaker. Proposed method is compared with baseline Deep Neural Network (DNN)-based system. Training of both the architectures and the evaluations were carried out on UA corpus. By analyzing the results, we observed that MMSE DiscoGAN outperforms DNN by 13.16% and 9.64% for male and female, respectively. Moreover, proposed GAN-based frameworks efficiently improve the intelligibility of dysarthric speech, and generate more naturalsounding speech compared to the DNN-based models. Keywords: Dysarthric Speech, Voice Conversion, DNN, DiscoGAN, ASR.","PeriodicalId":208527,"journal":{"name":"2020 International Conference on Signal Processing and Communications (SPCOM)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125551271","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: 8

Sample Complexity Lower Bounds for Compressive Sensing with Generative Models 基于生成模型的压缩感知样本复杂度下界

2020 International Conference on Signal Processing and Communications (SPCOM) Pub Date : 2020-07-01 DOI: 10.1109/SPCOM50965.2020.9179594

Zhaoqiang Liu, J. Scarlett

{"title":"Sample Complexity Lower Bounds for Compressive Sensing with Generative Models","authors":"Zhaoqiang Liu, J. Scarlett","doi":"10.1109/SPCOM50965.2020.9179594","DOIUrl":"https://doi.org/10.1109/SPCOM50965.2020.9179594","url":null,"abstract":"Recently, it has been shown that for compressive sensing, significantly fewer measurements may be required if the sparsity assumption is replaced by the assumption the unknown vector lies near the range of a suitably-chosen generative model. In particular, in (Bora et at., 2017) it was shown roughly O(k log L) random Gaussian measurements suffice for accurate recovery when the generative model is an L-Lipschitz function with bounded k-dimensional inputs, and O(kd log w) measurements suffice when the generative model is a k-input ReLU network with depth d and width w. In this paper, we establish corresponding algorithm-independent lower bounds on the sample complexity using tools from minimax statistical analysis. In accordance with the above upper bounds, our results are summarized as follows: (i) We construct an L-Lipschitz generative model capable of generating group-sparse signals, and show that the resulting necessary number of measurements is $Omega(klog L)$; (ii) Using similar ideas, we construct ReLU networks with high depth and/or high width for which the necessary number of measurements scales as $Omegaleft(k d frac{log w}{log n}right)$ (with output dimension n), and in some cases $Omega(k d log w)$. As a result, we establish that the scaling laws derived in (Bora et al$.,2017$) are optimal or near-optimal in the absence of further assumptions.","PeriodicalId":208527,"journal":{"name":"2020 International Conference on Signal Processing and Communications (SPCOM)","volume":"489 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128814978","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: 1

ℓ1/ℓ0 Regularized Conjugate Gradient Based Sparse Adaptive Algorithms 基于正则化共轭梯度的稀疏自适应算法

2020 International Conference on Signal Processing and Communications (SPCOM) Pub Date : 2020-07-01 DOI: 10.1109/SPCOM50965.2020.9179548

R. Das

引用次数: 0

Codes with Availability and different Localities 具有可用性和不同位置的代码

2020 International Conference on Signal Processing and Communications (SPCOM) Pub Date : 2020-07-01 DOI: 10.1109/SPCOM50965.2020.9179518

Ujwal Deep Kadiyam, Smarajit Das

引用次数: 0

Overlapped/Non-Overlapped Speech Transition Point Detection Using Bag-of-Audio-Words 基于bag -of- words的重叠/非重叠语音过渡点检测

2020 International Conference on Signal Processing and Communications (SPCOM) Pub Date : 2020-07-01 DOI: 10.1109/SPCOM50965.2020.9179591

Shikha Baghel, S. Prasanna, P. Guha

{"title":"Overlapped/Non-Overlapped Speech Transition Point Detection Using Bag-of-Audio-Words","authors":"Shikha Baghel, S. Prasanna, P. Guha","doi":"10.1109/SPCOM50965.2020.9179591","DOIUrl":"https://doi.org/10.1109/SPCOM50965.2020.9179591","url":null,"abstract":"Overlapped speech refers to an audio signal which contains speech of two or more speakers speaking simultaneously. Overlapped speech is one of the main sources of error for speaker diarization systems. This work presents an initial study to identify the transition points of overlapped to non-overlapped speech and vice-versa. Characteristics of overlapped and non-overlapped speech are examined in terms of the vocal tract system, excitation source, and modulation spectrum. The Hilbert envelope (HE) of Linear Prediction (LP) residual signal represents the excitation source characteristics of speech signal. The Sum of Ten Largest Peaks (STLP) of the spectrum and Mel-Frequency Cepstral Coefficients (MFCCs) represent the vocal tract shape information. The modulation spectrum energy (ModSE) captures the information of slowly varying temporal envelope of speech. A Bag-of-Audio-Words (BoAW) based approach is used to detect the transition points. News debates are one of the main sources of naturally occurred overlapped speech. Therefore, the present work is evaluated on Indian news debate scenario. A high Identification Rate (IR) and low Spurious Rate (SR) is observed when all the features are used simultaneously as a 16d feature(13-MFCCs, HE of LP residual, STLP and ModSE) for the detection task.","PeriodicalId":208527,"journal":{"name":"2020 International Conference on Signal Processing and Communications (SPCOM)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126882941","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: 0

Predominant Instrument Recognition in Polyphonic Music Using GMM-DNN Framework 基于GMM-DNN框架的复调音乐优势乐器识别

2020 International Conference on Signal Processing and Communications (SPCOM) Pub Date : 2020-07-01 DOI: 10.1109/SPCOM50965.2020.9179626

Roshni Ajayakumar, R. Rajan

引用次数: 5

Laser and Nonlinear Phase Noise Tracking and Estimation in Long Haul 400 Gbps Single Carrier PDM-16-QAM Systems using Multi-step Kalman Filter 基于多步卡尔曼滤波的400 Gbps单载波PDM-16-QAM系统激光和非线性相位噪声跟踪与估计

2020 International Conference on Signal Processing and Communications (SPCOM) Pub Date : 2020-07-01 DOI: 10.1109/SPCOM50965.2020.9179555

Srishti Sharma, P. Krishnamurthy

引用次数: 1

Online Service Policies for Content Delivery 内容交付的在线服务策略

2020 International Conference on Signal Processing and Communications (SPCOM) Pub Date : 2020-07-01 DOI: 10.1109/SPCOM50965.2020.9179501

Kota Srinivas Reddy, Arunabh Saxena, Sharayu Moharir, N. Karamchandani

引用次数: 0

Sliding Eigenvalue Decomposition for Non-stationary Signal Analysis 非平稳信号的滑动特征值分解

2020 International Conference on Signal Processing and Communications (SPCOM) Pub Date : 2020-07-01 DOI: 10.1109/SPCOM50965.2020.9179495

V. Singh, R. B. Pachori

引用次数: 1

Sparse Framework for Personal Sound Reproduction with Differential Phase Constraint 差分相位约束下个人声音再现的稀疏框架

2020 International Conference on Signal Processing and Communications (SPCOM) Pub Date : 2020-07-01 DOI: 10.1109/SPCOM50965.2020.9179508

Ajay Dagar, R. Hegde

引用次数: 0