Atnaujinkite slapukų nuostatas

El. knyga: Music Data Mining

4.50/5 (4 ratings by Goodreads)
Edited by (University of Miami, Coral Gables, Florida, USA), Edited by (University of Victoria, British Columbia, Canada), Edited by (Florida International University, Miami, USA)
Kitos knygos pagal šią temą:
Music Data MiningDidesnis 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“.

Li (computer science, Florida International U.) et al. present this study of music data mining. With the recent advances in digital technology and data distribution, music data mining has become an important issue in musicology and computing. Coverage includes data mining tasks, algorithms, audio feature extraction, data classification, instrument recognition, the effects of music on emotions and mood, peer-to-peer networks, indexing, hit song science, and symbolic musicology. The book is a valuable resource for those studying or in the field of musicology and data mining. Annotation ©2011 Book News, Inc., Portland, OR (booknews.com)

The research area of music information retrieval has gradually evolved to address the challenges of effectively accessing and interacting large collections of music and associated data, such as styles, artists, lyrics, and reviews. Bringing together an interdisciplinary array of top researchers, Music Data Mining presents a variety of approaches to successfully employ data mining techniques for the purpose of music processing.

The book first covers music data mining tasks and algorithms and audio feature extraction, providing a framework for subsequent chapters. With a focus on data classification, it then describes a computational approach inspired by human auditory perception and examines instrument recognition, the effects of music on moods and emotions, and the connections between power laws and music aesthetics. Given the importance of social aspects in understanding music, the text addresses the use of the Web and peer-to-peer networks for both music data mining and evaluating music mining tasks and algorithms. It also discusses indexing with tags and explains how data can be collected using online human computation games. The final chapters offer a balanced exploration of hit song science as well as a look at symbolic musicology and data mining.

The multifaceted nature of music information often requires algorithms and systems using sophisticated signal processing and machine learning techniques to better extract useful information. An excellent introduction to the field, this volume presents state-of-the-art techniques in music data mining and information retrieval to create novel ways of interacting with large music collections.

Recenzijos

" a useful survey for the reader specifically interested in MIR." Statistical Papers (2013) 54

"This book, as a collection of papers, brings together some of the leading scholars of the field to tackle a number of data mining techniques aiming mainly at data classification." Joonas Kauppinen, International Statistical Review, 2012

List of Figures
xiii
List of Tables
xvii
Preface xix
List of Contributors
xxiii
I Fundamental Topics
1(74)
1 Music Data Mining: An Introduction
3(40)
Tao Li
Lei Li
1.1 Music Data Sources
4(3)
1.2 An Introduction to Data Mining
7(6)
1.2.1 Data Management
8(1)
1.2.2 Data Preprocessing
9(1)
1.2.3 Data Mining Tasks and Algorithms
10(1)
1.2.3.1 Data Visualization
10(1)
1.2.3.2 Association Mining
11(1)
1.2.3.3 Sequence Mining
11(1)
1.2.3.4 Classification
11(1)
1.2.3.5 Clustering
12(1)
1.2.3.6 Similarity Search
12(1)
1.3 Music Data Mining
13(16)
1.3.1 Overview
13(1)
1.3.2 Music Data Management
14(2)
1.3.3 Music Visualization
16(1)
1.3.4 Music Information Retrieval
17(2)
1.3.5 Association Mining
19(1)
1.3.6 Sequence Mining
19(1)
1.3.7 Classification
20(5)
1.3.8 Clustering
25(1)
1.3.9 Music Summarization
26(1)
1.3.10 Advanced Music Data Mining Tasks
27(2)
1.4 Conclusion
29(14)
Bibliography
31(12)
2 Audio Feature Extraction
43(32)
George Tzanetakis
2.1 Audio Representations
44(7)
2.1.1 The Short-Time Fourier Transform
45(5)
2.1.2 Filter banks, Wavelets, and Other Time-Frequency Representations
50(1)
2.2 Timbral Texture Features
51(6)
2.2.1 Spectral Features
51(1)
2.2.2 Mel-Frequency Cepstral Coefficients
52(1)
2.2.3 Other Timbral Features
52(1)
2.2.4 Temporal Summarization
53(3)
2.2.5 Song-Level Modeling
56(1)
2.3 Rhythm Features
57(7)
2.3.1 Onset Strength Signal
59(1)
2.3.2 Tempo Induction and Beat Tracking
60(2)
2.3.3 Rhythm Representations
62(2)
2.4 Pitch/Harmony Features
64(1)
2.5 Other Audio Features
65(1)
2.6 Musical Genre Classification of Audio Signals
66(2)
2.7 Software Resources
68(1)
2.8 Conclusion
69(6)
Bibliography
69(6)
II Classification
75(142)
3 Auditory Sparse Coding
77(18)
Steven R. Ness
Thomas C. Walters
Richard F. Lyon
3.1 Introduction
78(3)
3.1.1 The Stabilized Auditory Image
80(1)
3.2 Algorithm
81(4)
3.2.1 Pole-Zero Filter Cascade
81(2)
3.2.2 Image Stabilization
83(1)
3.2.3 Box Cutting
83(1)
3.2.4 Vector Quantization
83(1)
3.2.5 Machine Learning
84(1)
3.3 Experiments
85(6)
3.3.1 Sound Ranking
85(4)
3.3.2 MIREX 2010
89(2)
3.4 Conclusion
91(4)
Bibliography
92(3)
4 Instrument Recognition
95(40)
Jayme Garcia Arnal Barbedo
4.1 Introduction
96(1)
4.2 Scope Delimitation
97(5)
4.2.1 Pitched and Unpitched Instruments
97(1)
4.2.2 Signal Complexity
97(3)
4.2.3 Number of Instruments
100(2)
4.3 Problem Basics
102(9)
4.3.1 Signal Segmentation
102(1)
4.3.2 Feature Extraction
103(2)
4.3.3 Classification Procedure
105(1)
4.3.3.1 Classification Systems
105(1)
4.3.3.2 Hierarchical and Flat Classifications
106(2)
4.3.4 Analysis and Presentation of Results
108(3)
4.4 Proposed Solutions
111(14)
4.4.1 Monophonic Case
111(8)
4.4.2 Polyphonic Case
119(6)
4.4.3 Other Relevant Work
125(1)
4.5 Future Directions
125(10)
Bibliography
127(8)
5 Mood and Emotional Classification
135(34)
Mitsunori Ogihara
Youngmoo Kim
5.1 Using Emotions and Moods for Music Retrieval
136(1)
5.2 Emotion and Mood: Taxonomies, Communication, and Induction
137(9)
5.2.1 What Is Emotion, What Is Mood?
137(1)
5.2.2 A Hierarchical Model of Emotions
138(1)
5.2.3 Labeling Emotion and Mood with Words and Its Issues
138(2)
5.2.4 Adjective Grouping and the Hevner Diagram
140(1)
5.2.5 Multidimensional Organizations of Emotion
140(2)
5.2.5.1 Three and Higher Dimensional Diagrams
142(3)
5.2.6 Communication and Induction of Emotion and Mood
145(1)
5.3 Obtaining Emotion and Mood Labels
146(4)
5.3.1 A Small Number of Human Labelers
146(1)
5.3.2 A Large Number of Labelers
147(1)
5.3.3 Mood Labels Obtained from Community Tags
148(1)
5.3.3.1 MIREX Mood Classification Data
148(1)
5.3.3.2 Latent Semantic Analysis on Mood Tags
149(1)
5.3.3.3 Screening by Professional Musicians
150(1)
5.4 Examples of Music Mood and Emotion Classification
150(8)
5.4.1 Mood Classfication Using Acoustic Data Analysis
150(1)
5.4.2 Mood Classification Based on Lyrics
151(2)
5.4.3 Mixing Audio and Tag Features for Mood Classification
153(1)
5.4.4 Mixing Audio and Lyrics for Mood Classification
154(2)
5.4.4.1 Further Exploratory Investigations with More Complex Feature Sets
156(1)
5.4.5 Exploration of Acoustic Cues Related to Emotions
157(1)
5.4.6 Prediction of Emotion Model Parameters
157(1)
5.5 Discussion
158(11)
Bibliography
160(9)
6 Zipf's Law, Power Laws, and Music Aesthetics
169(48)
Bill Manaris
Patrick Roos
Dwight Krehbiel
Thomas Zalonis
J.R. Armstrong
6.1 Introduction
171(1)
6.1.1 Overview
171(1)
6.2 Music Information Retrieval
172(3)
6.2.1 Genre and Author Classification
172(1)
6.2.1.1 Audio Features
172(1)
6.2.1.2 MIDI Features
173(1)
6.2.2 Other Aesthetic Music Classification Tasks
174(1)
6.3 Quantifying Aesthetics
175(3)
6.4 Zipf's Law and Power Laws
178(4)
6.4.1 Zipf's Law
178(3)
6.4.2 Music and Zipf's Law
181(1)
6.5 Power-Law Metrics
182(4)
6.5.1 Symbolic (MIDI) Metrics
182(1)
6.5.1.1 Regular Metrics
182(1)
6.5.1.2 Higher-Order Metrics
182(2)
6.5.1.3 Local Variability Metrics
184(1)
6.5.2 Timbre (Audio) Metrics
184(1)
6.5.2.1 Frequency Metric
184(1)
6.5.2.2 Signal Higher-Order Metrics
185(1)
6.5.2.3 Intrafrequency Higher-Order Metrics
185(1)
6.5.2.4 Interfrequency Higher-Order Metrics
185(1)
6.6 Automated Classification Tasks
186(10)
6.6.1 Popularity Prediction Experiment
187(1)
6.6.1.1 ANN Classification
187(4)
6.6.2 Style Classification Experiments
191(1)
6.6.2.1 Multiclass Classification
191(1)
6.6.2.2 Multiclass Classification (Equal Class Sizes)
192(1)
6.6.2.3 Binary-Class Classification (Equal Class Sizes)
193(1)
6.6.3 Visualization Experiment
194(1)
6.6.3.1 Self-Organizing Maps
194(2)
6.7 Annonique A Music Similarity Engine
196(1)
6.8 Psychological Experiments
197(12)
6.8.1 Earlier Assessment and Validation
198(1)
6.8.1.1 Artificial Neural Network Experiment
199(1)
6.8.1.2 Evolutionary Computation Experiment
199(1)
6.8.1.3 Music Information Retrieval Experiment
199(1)
6.8.2 Annonique Evaluation Experiments
200(1)
6.8.2.1 Methodology
200(1)
6.8.2.2 Results Psychological Ratings
201(2)
6.8.2.3 Results---Physiological Measures
203(1)
6.8.2.4 Discussion
204(4)
6.8.2.5 Final Thoughts
208(1)
6.9 Conclusion
209(8)
Acknowledgments
210(1)
Bibliography
211(6)
III Social Aspects of Music Data Mining
217(86)
7 Web-Based and Community-Based Music Information Extraction
219(32)
Markus Schedl
7.1 Approaches to Extract Information about Music
221(8)
7.1.1 Song Lyrics
222(3)
7.1.2 Country of Origin
225(2)
7.1.3 Band Members and Instrumentation
227(1)
7.1.4 Album Cover Artwork
228(1)
7.2 Approaches to Similarity Measurement
229(12)
7.2.1 Text-Based Approaches
229(1)
7.2.1.1 Term Profiles from Web Pages
230(2)
7.2.1.2 Collaborative Tags
232(2)
7.2.1.3 Song Lyrics
234(1)
7.2.2 Co-Occurrence-Based Approaches
235(1)
7.2.2.1 Web-Based Co-Occurrences and Page Counts
235(2)
7.2.2.2 Playlists
237(2)
7.2.2.3 Peer-to-Peer Networks
239(2)
7.3 Conclusion
241(10)
Acknowledgments
242(1)
Bibliography
242(9)
8 Indexing Music with Tags
251(30)
Douglas Turnbull
8.1 Introduction
251(1)
8.2 Music Indexing
252(3)
8.2.1 Indexing Text
252(2)
8.2.2 Indexing Music
254(1)
8.3 Sources of Tag-Based Music Information
255(6)
8.3.1 Conducting a Survey
256(1)
8.3.2 Harvesting Social Tags
257(1)
8.3.3 Playing Annotation Games
258(1)
8.3.4 Mining Web Documents
258(1)
8.3.5 Autotagging Audio Content
259(1)
8.3.6 Additional Remarks
259(2)
8.4 Comparing Sources of Music Information
261(6)
8.4.1 Social Tags: Last.fm
262(2)
8.4.2 Gaines: ListenGame
264(1)
8.4.3 Web Documents: Weight-Based Relevance Scoring
264(2)
8.4.4 Autotagging: Supervised Multiclass Labeling
266(1)
8.4.5 Summary
266(1)
8.5 Combining Sources of Music Information
267(7)
8.5.1 Ad-Hoc Combination Approaches
268(2)
8.5.2 Learned Combination Approaches
270(3)
8.5.3 Comparison
273(1)
8.6 Meerkat: A Semantic Music Discovery Engine
274(7)
Glossary
275(2)
Acknowledgments
277(1)
Bibliography
277(4)
9 Human Computation for Music Classification
281(22)
Edith Law
9.1 Introduction
281(2)
9.2 TagATune: A Music Tagging Game
283(8)
9.2.1 Input-Agreement Mechanism
283(2)
9.2.2 Fun Game, Noisy Data
285(1)
9.2.3 A Platform for Collecting Human Evaluation
286(1)
9.2.3.1 The TagATune Metric
287(1)
9.2.3.2 MIREX Special TagATune Evaluation
288(2)
9.2.3.3 Strength and Weaknesses
290(1)
9.3 Learning to Tag Using TagATune Data
291(8)
9.3.1 A Brief Introduction to Topic Models
292(1)
9.3.2 Leveraging Topic Models for Music Tagging
293(1)
9.3.2.1 Experimental Results
294(5)
9.4 Conclusion
299(4)
Bibliography
300(3)
IV Advanced Topics
303(44)
10 Hit Song Science
305(22)
Frangois Packet
10.1 An Inextricable Maze?
306(5)
10.1.1 Music Psychology and the Exposure Effect
307(2)
10.1.2 The Broadcaster/Listener Entanglement
309(1)
10.1.3 Social Influence
309(1)
10.1.4 Modeling the Life Span of Hits
310(1)
10.2 In Search of the Features of Popularity
311(3)
10.2.1 Features: The Case of Birds
312(1)
10.2.2 The Ground-Truth Issue
313(1)
10.2.3 Audio and Lyrics Features: The Initial Claim
314(1)
10.3 A Large-Scale Study
314(7)
10.3.1 Generic Audio Features
315(1)
10.3.2 Specific Audio Features
315(1)
10.3.3 Human Features
316(1)
10.3.4 The HiFind Database
316(1)
10.3.4.1 A Controlled Categorization Process
316(1)
10.3.4.2 Assessing Classifiers
317(1)
10.3.5 Experiment
317(1)
10.3.5.1 Design
317(1)
10.3.5.2 Random Oracles
318(1)
10.3.5.3 Evaluation of Acoustic Classifiers
318(1)
10.3.5.4 Inference from Human Data
319(1)
10.3.6 Summary
320(1)
10.4 Discussion
321(6)
Bibliography
323(4)
11 Symbolic Data Mining in Musicology
327(20)
Ian Knopke
Frauke Jurgensen
11.1 Introduction
327(1)
11.2 The Role of the Computer
328(1)
11.3 Symbolic Data Mining Methodology
329(2)
11.3.1 Denning the Problem
330(1)
11.3.2 Encoding and Normalization
330(1)
11.3.3 Musicological Interpretation
331(1)
11.4 Case Study: The Buxheim Organ Book
331(13)
11.4.1 Research Questions
332(3)
11.4.2 Encoding and Normalization
335(1)
11.4.3 Extraction, Filtering, and Interpretation
336(1)
11.4.3.1 Double Leading Tones
336(3)
11.4.3.2 Keyboard Tuning
339(5)
11.5 Conclusion
344(3)
Bibliography
344(3)
Index 347
Tao Li, Mitsunori Ogihara, George Tzanetakis
Daugiau apie elektronines knygas Daugiau apie elektronines knygas
Pastovi nuoroda: https://www.kriso.lt/db/97814398355552e.html
Raktažodžiai: