Information retrieval for music and motion /

Saved in:
Bibliographic Details
Author / Creator:Müller, Meinard.
Imprint:New York : Springer, 2007.
Description:xv, 313 p. : ill. (some col.) ; 24 cm.
Language:English
Subject:
Format: Print Book
URL for this record:http://pi.lib.uchicago.edu/1001/cat/bib/6810628
Hidden Bibliographic Details
ISBN:9783540740476
3540740473
Notes:Includes bibliographical references (p. [297]-308) and index.
Summary:"Meinard Muller details concepts and algorithms for robust and efficient information retrieval by means of two different types of multimedia data: waveform-based music data and human motion data. In Part I, he discusses in depth several approaches in music information retrieval, in particular general strategies as well as efficient algorithms for music synchronization, audio matching, and audio structure analysis. He also shows how the analysis results can be used in an advanced audio player to facilitate additional retrieval and browsing functionality. In Part II, he introduces a general and unified framework for motion analysis, retrieval, and classification, highlighting the design of suitable features, the notion of similarity used to compare data streams, and data organization. The detailed chapters at the beginning of each part give consideration to the interdisciplinary character of this field, covering information science, digital signal processing, audio engineering musicology, and computer graphics."--BOOK JACKET.
Table of Contents:
  • 1. Introduction
  • 1.1. Music Information Retrieval
  • 1.1.1. Outline of Part I
  • 1.1.2. Further Notes
  • 1.2. Motion Retrieval
  • 1.2.1. Outline of Part II
  • 1.2.2. Further Notes
  • 1.3. General Concepts
  • Part I. Analysis and Retrieval Techniques for Music Data
  • 2. Fundamentals on Music and Audio Data
  • 2.1. Music Representations
  • 2.1.1. Score Representation
  • 2.1.2. Sound, Waveform, and Audio Representation
  • 2.1.3. MIDI Representation
  • 2.2. Fourier Transform
  • 2.2.1. Signals and Signal Spaces
  • 2.2.2. Fourier Representations
  • 2.2.3. Discrete Fourier Transform
  • 2.2.4. Further Notes
  • 2.3. Digital Filters
  • 2.3.1. Convolution Filters
  • 2.3.2. Frequency Response
  • 2.3.3. Filter Specifications
  • 2.3.4. Examples
  • 2.3.5. Further Notes
  • 3. Pitch- and Chroma-Based Audio Features
  • 3.1. Pitch Features
  • 3.2. Local Energy (STMSP) and Onset Features
  • 3.3. Chroma and CENS Features
  • 3.4. Further Notes
  • 4. Dynamic Time Warping
  • 4.1. Classical DTW
  • 4.2. Variations of DTW
  • 4.2.1. Step Size Condition
  • 4.2.2. Local Weights
  • 4.2.3. Global Constraints
  • 4.2.4. Approximations
  • 4.3. Multiscale DTW
  • 4.4. Subsequence DTW
  • 4.5. Further Notes
  • 5. Music Synchronization
  • 5.1. Synchronization Tasks
  • 5.2. A Multiscale Approach to Audio Synchronization
  • 5.2.1. Audio Features
  • 5.2.2. Local Cost Measure
  • 5.2.3. Resolution Levels and [delta]-Neighborhood
  • 5.2.4. Experimental Results
  • 5.2.5. Enhancing Cost Matrices
  • 5.3. Onset-Based Score-Audio Synchronization
  • 5.3.1. Audio Features
  • 5.3.2. Local Similarity Measure
  • 5.3.3. Matching Model and Alignment
  • 5.3.4. Efficiency and Anchor Matches
  • 5.3.5. Experimental Results
  • 5.4. Further Notes
  • 6. Audio Matching
  • 6.1. Diagonal Audio Matching
  • 6.1.1. Audio Features
  • 6.1.2. Basic Matching Procedure
  • 6.1.3. Global Variations in Tempo and Key
  • 6.1.4. Efficient Implementation
  • 6.2. Experimental Results for Diagonal Audio Matching
  • 6.2.1. Representative Matching Results
  • 6.2.2. Dependence on Query Length
  • 6.3. Codebook Selection for CENS Features
  • 6.3.1. Codebook Selection by Unsupervised Learning
  • 6.3.2. Codebook Selection Based on Musical Knowledge
  • 6.4. Index-Based Audio Matching
  • 6.4.1. Exact Matches
  • 6.4.2. Fault Tolerance Mechanisms
  • 6.4.3. Retrieval Scenario and Ranking
  • 6.5. Experimental Results for Index-Based Audio Matching
  • 6.5.1. Diagonal vs. Index-Based Matching
  • 6.5.2. Comparison of Codebooks
  • 6.5.3. Running Times
  • 6.6. Further Notes
  • 7. Audio Structure Analysis
  • 7.1. General Strategy and Notation
  • 7.2. Enhancing Similarity Matrices
  • 7.3. Path Extraction
  • 7.4. Global Structure Analysis
  • 7.5. Experiments
  • 7.5.1. General Results
  • 7.5.2. Running Time Behavior
  • 7.5.3. Transpositions
  • 7.6. Further Notes
  • 8. SyncPlayer: An Advanced Audio Player
  • 8.1. Overview
  • 8.2. SyncPlayer Server
  • 8.3. SyncPlayer Client
  • 8.4. Further Notes
  • Part II. Analysis and Retrieval Techniques for Motion Data
  • 9. Fundamentals on Motion Capture Data
  • 9.1. Motion Capture Data
  • 9.2. Similarity Aspects
  • 9.3. Kinematic Chains
  • 9.3.1. Formal Definition
  • 9.3.2. Forward Kinematics
  • 9.3.3. Animated Kinematic Chains
  • 9.3.4. Further Notes
  • 9.4. Rotations
  • 9.4.1. Basic Definitions and Properties
  • 9.4.2. Euler Angles
  • 9.4.3. Quaternions
  • 9.4.4. Further Notes
  • 10. DTW-Based Motion Comparison and Retrieval
  • 10.1. Local Distance Measures
  • 10.1.1. Quaternion-Based Pose Distance
  • 10.1.2. 3D Point Cloud Distance
  • 10.1.3. Examples
  • 10.2. DTW-Based Motion Warping
  • 10.3. Motion Retrieval Based on Self-Similarity
  • 10.4. Further Notes
  • 11. Relational Features and Adaptive Segmentation
  • 11.1. Relational Features
  • 11.1.1. A Basic Example
  • 11.1.2. Generic Features
  • 11.1.3. Threshold Selection
  • 11.1.4. Example for Some Feature Set
  • 11.2. Adaptive Segmentation
  • 11.3. Further Notes
  • 12. Index-Based Motion Retrieval
  • 12.1. Indexing, Queries, and Hits
  • 12.1.1. Inverted File Index
  • 12.1.2. Exact Queries and Exact Hits
  • 12.1.3. Fuzzy Queries and Fuzzy Hits
  • 12.1.4. Adaptive Fuzzy Hits
  • 12.2. QBE Motion Retrieval
  • 12.2.1. Query and Retrieval Mechanism
  • 12.2.2. Indexing Stage
  • 12.2.3. Experimental Results
  • 12.2.4. Ranking Strategies
  • 12.3. Further Applications
  • 12.3.1. Accelerating DTW-Based Motion Alignment
  • 12.3.2. Keyframe-Based Preselection
  • 12.3.3. Toward Scene Descriptions
  • 12.4. Further Notes
  • 12.4.1. Problems and Limitations
  • 12.4.2. Related Work
  • 13. Motion Templates
  • 13.1. Basic Definitions and Properties
  • 13.2. MT Learning Procedure: Overview
  • 13.3. MT Learning Procedure: Technical Details
  • 13.3.1. Reference-Based WMT Warping
  • 13.3.2. WMT Unwarping
  • 13.3.3. Reference-Based WMT Averaging
  • 13.3.4. Reference-Free WMT Averaging
  • 13.4. Experimental Results
  • 13.4.1. Motion Class Database
  • 13.4.2. WMT Computation and Time Complexity
  • 13.4.3. Examples
  • 13.5. Further Notes
  • 14. MT-Based Motion Annotation and Retrieval
  • 14.1. MT-Based Matching
  • 14.2. MT-Based Annotation
  • 14.3. MT-Based Retrieval
  • 14.4. Keyframe-Based Preprocessing
  • 14.5. Comparison to Other Retrieval Methods
  • 14.6. Further Notes
  • References
  • Index