Keywords:
Multimedia systems-Congresses.
;
Electronic books.
Type of Medium:
Online Resource
Pages:
1 online resource (369 pages)
Edition:
1st ed.
ISBN:
9783030037482
Series Statement:
Smart Innovation, Systems and Technologies Series ; v.110
URL:
https://ebookcentral.proquest.com/lib/geomar/detail.action?docID=5596968
DDC:
006.7
Language:
English
Note:
Intro -- Preface -- Conference Organization -- Conference Founders -- Honorary Chairs -- Advisory Committee -- General Chairs -- Program Chairs -- Invited Session Chairs -- Publication Chairs -- Electronic Media Chairs -- Finance Chair -- Program Committee Members -- Contents -- Health Informatics, Intelligent Data Hiding, and Deep Learning for Information Hiding -- An Improved High-Capacity ECG Steganography with Smart Offset Coefficients -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Bit Embedding -- 3.2 Bit Extraction -- 3.3 Alterative High-Perceived Quality Approach -- 4 Experimental Results -- 5 Conclusion -- References -- Preview-Versioned Essential Secret Image Sharing -- Abstract -- 1 Introduction -- 2 The Proposed Method -- 3 Experimental Results and Comparisons -- 4 Conclusions -- References -- Visual Cryptography with QR-Code Transparencies -- Abstract -- 1 Introduction -- 2 The Proposed Method -- 3 Experimental Results -- 4 Conclusions -- References -- Solving the Multiple Charging Vehicles Scheduling Problem for Wireless Rechargeable Sensor Networks Using Cuckoo Search Approach -- Abstract -- 1 Introduction -- 2 Related Works -- 3 The Proposed Method -- 3.1 Objective Function -- 3.2 Nest Representation -- 3.3 K-center Grouping -- 4 Experimental Results and Comparisons -- 5 Conclusions -- References -- An Image Steganography Algorithm Based on Pixel Block Difference and Variable Modulus Function -- Abstract -- 1 Introduction -- 2 A Steganography Algorithm Based on PBVD -- 3 Analysis and Discussion of Algorithm Examples -- 4 Experiments and Analysis -- 4.1 Algorithm Embedded Capacity -- 4.2 Secret Digital Image Quality -- 5 Conclusion -- Acknowledgements -- References -- Attack Pattern Mining Algorithm Based on Fuzzy Clustering and Sequence Pattern from Security Log -- Abstract -- 1 Introduction.
,
2 Attack Pattern Mining Algorithm Based on Fuzzy Clustering -- 2.1 Generating Security Log Sequence Set -- 2.2 Frequent Sequence Mining from Sequence Set -- 3 Experiment and Analysis -- 3.1 Experiment Result -- 3.2 Result Analysis -- 4 Conclusion -- Acknowledgements -- References -- Recent Advances in Information Hiding and Signal Processing for Audio and Speech Signals -- An Interrogation Speech Manipulation Detection Method Using Speech Fingerprinting and Watermarking -- Abstract -- 1 Introduction -- 2 An Interrogation Speech Manipulation Detection Method Using Speech Fingerprinting -- 3 Manipulation Detection Accuracy Evaluations -- 4 Simulation of Noise and Reverberation -- 5 Conclusion -- Acknowledgments -- References -- Digital Audio Watermarking Method Based on Singular Spectrum Analysis with Automatic Parameter Estimation Using a Convolutional Neural Network -- 1 Introduction -- 2 Previously Proposed Framework -- 2.1 Embedding Process and Extraction Process -- 2.2 Differential Evolution -- 3 Proposed Framework -- 3.1 CNN-Based Parameter Estimation -- 3.2 Extraction Process -- 4 Evaluations -- 4.1 Parameter Estimation Accuracy -- 4.2 Robustness Evaluation -- 4.3 Sound Quality Evaluation -- 5 Discussion -- 6 Conclusion -- References -- Muting Machine Speech Using Audio Watermarking -- 1 Introduction -- 2 Proposed Method -- 2.1 Overview -- 2.2 Embedding the Watermark -- 3 Experiment -- 3.1 Experimental Setup -- 3.2 Results -- 4 Conclusion -- References -- Leveraging a Small Corpus by Different Frame Shifts for Training of a Speech Recognizer -- 1 Introduction -- 2 Frame-Based Speech Analysis and Recognition -- 3 Compensation of Contingency of Window Position -- 3.1 Effect of Window Position Difference -- 3.2 Compensation of the Window Position Mismatch -- 3.3 Experiment -- 4 Longer Window and Frame Shift -- 4.1 The Merit of Longer Frame Shift.
,
4.2 Experimental Conditions -- 4.3 Results -- 5 Conclusion -- References -- Advances in Speech and Language Processing -- Evaluation of English Speech Recognition for Japanese Learners Using DNN-Based Acoustic Models -- Abstract -- 1 Introduction -- 2 CALL Systems and Recognition of Non-native Speech -- 3 DNN-Based Acoustic Modeling of Non-native Speech -- 4 Experiments with ERJ Database -- 4.1 Data Preparation in ERJ Database -- 4.2 Language Modeling -- 4.3 Results of Monophone and Triphone Training -- 4.4 Results of DNN Training -- 4.5 Relationship Between Proficiency and WER -- 5 Conclusions -- Acknowledgements -- References -- A Study on a Spoken Dialogue System with Cooperative Emotional Speech Synthesis Using Acoustic and Linguistic Information -- 1 Introduction -- 2 Dialogue System with the Cooperative Emotion Labeling -- 2.1 Overview of the Proposed Dialogue System -- 2.2 Emotion Labeling Based on the Linguistic Information -- 2.3 Emotion Labeling Based on the Acoustic Information -- 3 Dialog Experiment Based on the Scenarios for the Subjective Evaluation -- 3.1 Scenarios Prepared for the Experiment -- 3.2 Experimental Procedure and Conditions -- 3.3 Experimental Result and Discussion -- 4 Conclusion -- References -- Comparison of Speech Recognition Performance Between Kaldi and Google Cloud Speech API -- 1 Introduction -- 2 Speech Recognition Systems -- 2.1 Kaldi -- 2.2 Google Cloud Speech API -- 3 Experimental Conditions -- 3.1 Speech Recognition Model of Kaldi -- 3.2 Evaluation Data -- 4 Preprocessing of Recognition Results -- 5 Results -- 5.1 WER -- 5.2 RTF -- 6 Conclusion -- References -- Melody Completion Based on Convolutional Neural Networks and Generative Adversarial Learning -- 1 Introduction -- 2 Representation of Melody and Chord -- 2.1 Melody Representation -- 2.2 Chord -- 2.3 Dataset -- 3 Melody Completion Network.
,
3.1 Architecture -- 3.2 Training -- 4 Experiment -- 4.1 Experimental Condition -- 4.2 Results -- 5 Conclusion -- References -- Segmental Pitch Control Using Speech Input Based on Differential Contexts and Features for Customizable Neural Speech Synthesis -- 1 Introduction -- 1.1 F0 Modeling with Differential F0 Contexts and Features in Neural Speech Synthesis -- 2 Segmental Pitch Control of Synthetic Speech Using User Input -- 3 Experiments -- 3.1 Experimental Conditions -- 3.2 Pitch Control Under Ideal Condition -- 3.3 Pitch Control Using User Speech Input -- 4 Conclusions -- References -- Two-Stage Sequence-to-Sequence Neural Voice Conversion with Low-to-High Definition Spectrogram Mapping -- 1 Introduction -- 2 Two-Stage Voice Conversion with U-Net and Pix2pix -- 2.1 Framework Overview -- 2.2 First-Stage: Segmental Feature Conversion with U-Net -- 2.3 Second-Stage: Low-to-High Spectrogram Mapping with Pix2pix -- 3 Experiments -- 3.1 Experimental Conditions -- 3.2 Objective Evaluation -- 3.3 Subjective Evaluation -- 4 Conclusions -- References -- Improvement of Accent Sandhi Rules Based on Japanese Accent Dictionaries -- Abstract -- 1 Introduction -- 2 Japanese Accent Sandhi Rules -- 2.1 Japanese Accent and Accent Sandhi -- 2.2 Conventional Accent Sandhi Rules -- 3 Improvement of Rules Based on Japanese Accent Dictionaries -- 3.1 Modifications of Conventional Rules -- 3.2 Addition of New Rules -- 4 Accent Estimation Experiment -- 5 Conclusion -- References -- Data Collection and Analysis for Automatically Generating Record of Human Behaviors by Environmental Sound Recognition -- Abstract -- 1 Introduction -- 2 Collection of the Environmental Sound -- 3 Classification of Behavioral Classes Based on Environmental Sound Around Wearer -- 3.1 Conditions of Recognition Experiment -- 3.2 Training of the Classifier.
,
3.3 Influence of Window Size of Acoustic Feature -- 4 Analysis of Acoustic Similarity Between the Target Classes -- 4.1 Conditions of Analysis -- 4.2 Result of Analysis -- 5 Conclusion -- References -- DNN-Based Talking Movie Generation with Face Direction Consideration -- 1 Introduction -- 2 Parametric Face Animation Synthesis Based on DNN -- 2.1 Analysis and Synthesis of a Face Image Using AAM -- 2.2 Modeling and Generation of the AAM Parameters Using DNN -- 2.3 Generation of a Face Image Considering the Face Direction -- 3 Experiments -- 3.1 Experimental Conditions -- 3.2 Result -- 4 Conclusion -- References -- Emerging Trends in Multimedia Systems and Multimedia System with Intelligent Computing -- A P2P Multimedia Service System Based on Mesh-Chords -- Abstract -- 1 Introduction -- 2 System Design and Implementation -- 2.1 Architecture of P2P Multimedia Service System -- 2.2 Identical Hash Mapping -- 2.3 Mesh-Chords -- 2.4 Initialization of Mesh-Chords -- 3 Mesh-Chords Routing Algorithm -- 4 Experiment and Evaluation -- 5 Conclusions -- References -- Denoising of ECG Signal with Power Line and EMG Interference Based on Ensemble Empirical Mode Decomposition -- Abstract -- 1 Introduction -- 2 Method -- 2.1 ECG Signal -- 2.2 EMD Algorithm -- 2.3 EEMD Algorithm -- 2.4 Grey System Noise Estimation Method -- 2.5 ECG Noise Cancellation Process -- 2.6 Performance Indicator -- 3 Results -- 4 Conclusions -- Acknowledgment -- References -- Using the Photoplethysmography Technique to Improve the Accuracy of LVET Measurement in the ICG Technique -- Abstract -- 1 Introduction -- 2 Method -- 2.1 Hardware Architecture -- 2.2 Signal Capture -- 2.3 ICG Calculation Formula -- 2.4 Experimental Steps -- 3 Results and Discussions -- 4 Conclusions -- Acknowledgment -- References -- Network Anomaly Detection Based on Artificial Intelligence -- Abstract.
,
1 Introduction.
Permalink