Atnaujinkite slapukų nuostatas

El. knyga: Music Emotion Recognition

5.00/5 (6 ratings by Goodreads)
,
Kitos knygos pagal šią temą:
Music Emotion RecognitionDidesnis paveikslėlis
Kitos knygos pagal šią temą:

DRM apribojimai

  • Kopijuoti:

    neleidžiama

  • Spausdinti:

    neleidžiama

  • El. knygos naudojimas:

    Skaitmeninių teisių valdymas (DRM)
    Leidykla pateikė šią knygą šifruota forma, o tai reiškia, kad norint ją atrakinti ir perskaityti reikia įdiegti nemokamą programinę įrangą. Norint skaityti šią el. knygą, turite susikurti Adobe ID . Daugiau informacijos  čia. El. knygą galima atsisiųsti į 6 įrenginius (vienas vartotojas su tuo pačiu Adobe ID).

    Reikalinga programinė įranga
    Norint skaityti šią el. knygą mobiliajame įrenginyje (telefone ar planšetiniame kompiuteryje), turite įdiegti šią nemokamą programėlę: PocketBook Reader (iOS / Android)

    Norint skaityti šią el. knygą asmeniniame arba „Mac“ kompiuteryje, Jums reikalinga  Adobe Digital Editions “ (tai nemokama programa, specialiai sukurta el. knygoms. Tai nėra tas pats, kas „Adobe Reader“, kurią tikriausiai jau turite savo kompiuteryje.)

    Negalite skaityti šios el. knygos naudodami „Amazon Kindle“.

Providing a complete review of existing work in music emotion developed in psychology and engineering, Music Emotion Recognition explains how to account for the subjective nature of emotion perception in the development of automatic music emotion recognition (MER) systems. Among the first publications dedicated to automatic MER, it begins with a comprehensive introduction to the essential aspects of MERincluding background, key techniques, and applications.

This ground-breaking reference examines emotion from a dimensional perspective. It defines emotions in music as points in a 2D plane in terms of two of the most fundamental emotion dimensions according to psychologistsvalence and arousal. The authors present a computational framework that generalizes emotion recognition from the categorical domain to real-valued 2D space. They also:











Introduce novel emotion-based music retrieval and organization methods Describe a ranking-base emotion annotation and model training method Present methods that integrate information extracted from lyrics, chord sequence, and genre metadata for improved accuracy Consider an emotion-based music retrieval system that is particularly useful for mobile devices

The book details techniques for addressing the issues related to: the ambiguity and granularity of emotion description, heavy cognitive load of emotion annotation, subjectivity of emotion perception, and the semantic gap between low-level audio signal and high-level emotion perception. Complete with more than 360 useful references, 12 example MATLAB® codes, and a listing of key abbreviations and acronyms, this cutting-edge guide supplies the technical understanding and tools needed to develop your own automatic MER system based on the automatic recognition model.
Preface xi
Abbreviations xiii
1 Introduction 1(14)
1.1 Importance of Music Emotion Recognition
1(3)
1.2 Recognizing the Perceived Emotion of Music
4(2)
1.3 Issues of Music Emotion Recognition
6(6)
1.3.1 Ambiguity and Granularity of Emotion Description
6(1)
1.3.2 Heavy Cognitive Load of Emotion Annotation
7(1)
1.3.3 Subjectivity of Emotional Perception
8(1)
1.3.4 Semantic Gap between Low-Level Audio Signal and High-Level Human Perception
9(3)
1.4 Summary
12(3)
2 Overview of Emotion Description and Recognition 15(20)
2.1 Emotion Description
15(6)
2.1.1 Categorical Approach
16(2)
2.1.2 Dimensional Approach
18(2)
2.1.3 Music Emotion Variation Detection
20(1)
2.2 Emotion Recognition
21(11)
2.2.1 Categorical Approach
22(7)
2.2.1.1 Data Collection
23(2)
2.2.1.2 Data Preprocessing
25(1)
2.2.1.3 Subjective Test
26(2)
2.2.1.4 Feature Extraction
28(1)
2.2.1.5 Model Training
28(1)
2.2.2 Dimensional Approach
29(2)
2.2.3 Music Emotion Variation Detection
31(1)
2.3 Summary
32(3)
3 Music Features 35(20)
3.1 Energy Features
36(1)
3.2 Rhythm Features
37(5)
3.3 Temporal Features
42(2)
3.4 Spectrum Features
44(7)
3.5 Harmony Features
51(3)
3.6 Summary
54(1)
4 Dimensional MER by Regression 55(26)
4.1 Adopting the Dimensional Conceptualization of Emotion
55(2)
4.2 VA Prediction
57(2)
4.2.1 Weighted Sum of Component Functions
57(1)
4.2.2 Fuzzy Approach
58(1)
4.2.3 System Identification Approach (System ID)
58(1)
4.3 The Regression Approach
59(3)
4.3.1 Regression Theory
59(1)
4.3.2 Problem Formulation
60(1)
4.3.3 Regression Algorithms
60(3)
4.3.3.1 Multiple Linear Regression
60(1)
4.3.3.2 E-Support Vector Regression
61(1)
4.3.3.3 AdaBoost Regression Tree (AdaBoost.RT)
62(1)
4.4 System Overview
62(1)
4.5 Implementation
63(5)
4.5.1 Data Collection
63(2)
4.5.2 Feature Extraction
65(2)
4.5.3 Subjective Test
67(1)
4.5.4 Regressor Training
67(1)
4.6 Performance Evaluation
68(11)
4.6.1 Consistency Evaluation of the Ground Truth
68(2)
4.6.2 Data Transformation
70(1)
4.6.3 Feature Selection
71(3)
4.6.4 Accuracy of Emotion Recognition
74(3)
4.6.5 Performance Evaluation for Music Emotion Variation Detection
77(1)
4.6.6 Performance Evaluation for Emotion Classification
78(1)
4.7 Summary
79(2)
5 Ranking-Based Emotion Annotation and Model Training 81(26)
5.1 Motivation
81(1)
5.2 Ranking-Based Emotion Annotation
82(2)
5.3 Computational Model for Ranking Music by Emotion
84(6)
5.3.1 Learning-to-Rank
85(1)
5.3.2 Ranking Algorithms
85(5)
5.3.2.1 RankSVM
85(1)
5.3.2.2 ListNet
85(2)
5.3.2.3 RBF-ListNet
87(3)
5.4 System Overview
90(1)
5.5 Implementation
90(6)
5.5.1 Data Collection
92(3)
5.5.2 Feature Extraction
95(1)
5.6 Performance Evaluation
96(8)
5.6.1 Cognitive Load of Annotation
97(1)
5.6.2 Accuracy of Emotion Recognition
98(6)
5.6.2.1 Comparison of Different Feature Representations
99(1)
5.6.2.2 Comparison of Different Learning Algorithms
100(2)
5.6.2.3 Sensitivity Test
102(2)
5.6.3 Subjective Evaluation of the Prediction Result
104(1)
5.7 Discussion
104(1)
5.8 Summary
105(2)
6 Fuzzy Classification of Music Emotion 107(12)
6.1 Motivation
107(1)
6.2 Fuzzy Classification
108(4)
6.2.1 Fuzzy k-NN Classifier
108(1)
6.2.2 Fuzzy Nearest-Mean Classifier
109(3)
6.3 System Overview
112(1)
6.4 Implementation
113(1)
6.4.1 Data Collection
113(1)
6.4.2 Feature Extraction and Feature Selection
113(1)
6.5 Performance Evaluation
114(3)
6.5.1 Accuracy of Emotion Classification
114(1)
6.5.2 Music Emotion Variation Detection
114(3)
6.6 Summary
117(2)
7 Personalized MER and Groupwise MER 119(16)
7.1 Motivation
119(2)
7.2 Personalized MER
121(1)
7.3 Groupwise MER
122(2)
7.4 Implementation
124(4)
7.4.1 Data Collection
124(2)
7.4.2 Personal Information Collection
126(1)
7.4.3 Feature Extraction
127(1)
7.5 Performance Evaluation
128(6)
7.5.1 Performance of the General Method
128(2)
7.5.2 Performance of GWMER
130(1)
7.5.3 Performance of PMER
130(4)
7.6 Summary
134(1)
8 Two-Layer Personalization 135(10)
8.1 Problem Formulation
135(1)
8.2 Bag-of-Users Model
136(1)
8.3 Residual Modeling and Two-Layer Personalization Scheme
137(2)
8.4 Performance Evaluation
139(4)
8.5 Summary
143(2)
9 Probability Music Emotion Distribution Prediction 145(28)
9.1 Motivation
145(1)
9.2 Problem Formulation
146(2)
9.3 The KDE-Based Approach to Music Emotion Distribution Prediction
148(9)
9.3.1 Ground Truth Collection
148(2)
9.3.2 Regressor Training
150(3)
9.3.2.1 v-Support Vector Regression
151(1)
9.3.2.2 Gaussian Process Regression
151(2)
9.3.3 Regressor Fusion
153(3)
9.3.3.1 Weighted by Performance
153(1)
9.3.3.2 Optimization
154(2)
9.3.4 Output of Emotion Distribution
156(1)
9.4 Implementation
157(4)
9.4.1 Data Collection
157(1)
9.4.2 Feature Extraction
157(4)
9.5 Performance Evaluation
161(6)
9.5.1 Comparison of Different Regression Algorithms
161(1)
9.5.2 Comparison of Different Distribution Modeling Methods
162(3)
9.5.3 Comparison of Different Feature Representations
165(1)
9.5.4 Evaluation of Regressor Fusion
166(1)
9.6 Discussion
167(5)
9.7 Summary
172(1)
10 Lyrics Analysis and Its Application to MER 173(14)
10.1 Motivation
173(1)
10.2 Lyrics Feature Extraction
174(5)
10.2.1 Uni-Gram
175(1)
10.2.2 Probabilistic Latent Semantic Analysis (PLSA)
176(1)
10.2.3 Bi-Gram
177(2)
10.3 Multimodal MER System
179(2)
10.4 Performance Evaluation
181(3)
10.4.1 Comparison of Multimodal Fusion Methods
181(2)
10.4.2 Performance of PLSA Model
183(1)
10.4.3 Performance of Bi-Gram Model
184(1)
10.5 Summary
184(3)
11 Chord Recognition and Its Application to MER 187(10)
11.1 Chord Recognition
187(4)
11.1.1 Beat Tracking and PCP Extraction
188(1)
11.1.2 Hidden Markov Model and N-Gram Model
188(2)
11.1.3 Chord Decoding
190(1)
11.2 Chord Features
191(2)
11.2.1 Longest Common Chord Subsequence
192(1)
11.2.2 Chord Histogram
192(1)
11.3 System Overview
193(1)
11.4 Performance Evaluation
193(3)
11.4.1 Evaluation of Chord Recognition System
193(1)
11.4.2 Accuracy of Emotion Classification
194(2)
11.5 Summary
196(1)
12 Genre Classification and Its Application to MER 197(10)
12.1 Motivation
197(1)
12.2 Two-Layer Music Emotion Classification
198(1)
12.3 Performance Evaluation
199(6)
12.3.1 Data Collection
199(1)
12.3.2 Analysis of the Correlation between Genre and Emotion
200(3)
12.3.3 Evaluation of the Two-Layer Emotion Classification Scheme
203(5)
12.3.3.1 Computational Model
203(1)
12.3.3.2 Evaluation Measures
203(1)
12.3.3.3 Results
204(1)
12.4 Summary
205(2)
13 Music Retrieval in the Emotion Plane 207(6)
13.1 Emotion-Based Music Retrieval
207(1)
13.2 2D Visualization of Music
208(1)
13.3 Retrieval Methods
208(2)
13.3.1 Query by Emotion Point (QBEP)
209(1)
13.3.2 Query by Emotion Trajectory (QBET)
209(1)
13.3.3 Query by Artist and Emotion (QBAE)
209(1)
13.3.4 Query by Lyrics and Emotion (QBLE)
209(1)
13.4 Implementation
210(2)
13.5 Summary
212(1)
14 Future Research Directions 213(6)
14.1 Exploiting Vocal Timbre for MER
213(1)
14.2 Emotion Distribution Prediction Based on Rankings
214(1)
14.3 Personalized Emotion-Based Music Retrieval
215(1)
14.4 Situational Factors of Emotion Perception
215(1)
14.5 Connections between Dimensional and Categorical MER
216(1)
14.6 Music Retrieval and Organization in 3D Emotion Space
216(3)
References 219(18)
Index 237
Yi-Hsuan Yang received a Ph.D. in Communication Engineering from National Taiwan University in 2010. His research interests include multimedia information retrieval, music analysis, machine learning, and affective computing. He has published over 30 technical papers in the above areas. Dr. Yang was awarded MediaTek Fellowship in 2009 and Microsoft Research Asia Fellowship in 2008.

Homer H. Chen received a Ph.D. in Electrical and Computer Engineering from the University of Illinois at Urbana- Champaign. Since August 2003, he has been with the College of Electrical Engineering and Computer Science, National Taiwan University, where he is Irving T. Ho Chair Professor. Prior to that, he held various R&D management and engineering positions with US companies over a period of 17 years, including AT&T Bell Labs, Rockwell Science Center, iVast, and Digital Island. He was a US delegate for ISO and ITU standards committees and contributed to the development of many new interactive multimedia technologies that are now part of the MPEG-4 and JPEG-2000 standards. His professional interests lie in the broad area of multimedia signal processing and communications.

Dr. Chen is an Associate Editor of IEEE Transactions on Circuits and Systems for Video Technology. He served as Associate Editor of IEEE Transactions on Image Processing from 1992 to 1994, Guest Editor of IEEE Transactions on Circuits and Systems for Video Technology in 1999, and an Associate Editorial of Pattern Recognition from 1989 to 1999. He is an IEEE Fellow.
Daugiau apie elektronines knygas Daugiau apie elektronines knygas
Pastovi nuoroda: https://www.kriso.lt/db/97814398504732e.html
Raktažodžiai: