Lerch, Alexander,
An introduction to audio content analysis : applications in signal processing and music informatics / Alexander Lerch. - 1 PDF (xxii, 248 pages).
Includes bibliographical references.
Machine generated contents note: 1.1.Audio Content -- 1.2.A Generalized Audio Content Analysis System -- 2.1.Audio Signals -- 2.1.1.Periodic Signals -- 2.1.2.Random Signals -- 2.1.3.Sampling and Quantization -- 2.1.4.Statistical Signal Description -- 2.2.Signal Processing -- 2.2.1.Convolution -- 2.2.2.Block-Based Processing -- 2.2.3.Fourier Transform -- 2.2.4.Constant Q Transform -- 2.2.5.Auditory Filterbanks -- 2.2.6.Correlation Function -- 2.2.7.Linear Prediction -- 3.1.Audio Pre-Processing -- 3.1.1.Down-Mixing -- 3.1.2.DC Removal -- 3.1.3.Normalization -- 3.1.4.Down-Sampling -- 3.1.5.Other Pre-Processing Options -- 3.2.Statistical Properties -- 3.2.1.Arithmetic Mean -- 3.2.2.Geometric Mean -- 3.2.3.Harmonic Mean -- 3.2.4.Generalized Mean -- 3.2.5.Centroid -- 3.2.6.Variance and Standard Deviation -- 3.2.7.Skewness -- 3.2.8.Kurtosis -- 3.2.9.Generalized Central Moments -- 3.2.10.Quantiles and Quantile Ranges -- 3.3.Spectral Shape -- 3.3.1.Spectral Rolloff -- Contents note continued: 3.3.2.Spectral Flux -- 3.3.3.Spectral Centroid -- 3.3.4.Spectral Spread -- 3.3.5.Spectral Decrease -- 3.3.6.Spectral Slope -- 3.3.7.Mel Frequency Cepstral Coefficients -- 3.4.Signal Properties -- 3.4.1.Tonalness -- 3.4.2.Autocorrelation Coefficients -- 3.4.3.Zero Crossing Rate -- 3.5.Feature Post-Processing -- 3.5.1.Derived Features -- 3.5.2.Normalization and Mapping -- 3.5.3.Subfeatures -- 3.5.4.Feature Dimensionality Reduction -- 4.1.Human Perception of Intensity and Loudness -- 4.2.Representation of Dynamics in Music -- 4.3.Features -- 4.3.1.Root Mean Square -- 4.4.Peak Envelope -- 4.5.Psycho-Acoustic Loudness Features -- 4.5.1.EBU R128 -- 5.1.Human Perception of Pitch -- 5.1.1.Pitch Scales -- 5.1.2.Chroma Perception -- 5.2.Representation of Pitch in Music -- 5.2.1.Pitch Classes and Names -- 5.2.2.Intervals -- 5.2.3.Root Note, Mode, and Key -- 5.2.4.Chords and Harmony -- 5.2.5.The Frequency of Musical Pitch -- 5.3.Fundamental Frequency Detection -- Contents note continued: 5.3.1.Detection Accuracy -- 5.3.2.Pre-Processing -- 5.3.3.Monophonic Input Signals -- 5.3.4.Polyphonic Input Signals -- 5.4.Tuning Frequency Estimation -- 5.5.Key Detection -- 5.5.1.Pitch Chroma -- 5.5.2.Key Recognition -- 5.6.Chord Recognition -- 6.1.Human Perception of Temporal Events -- 6.1.1.Onsets -- 6.1.2.Tempo and Meter -- 6.1.3.Rhythm -- 6.1.4.Timing -- 6.2.Representation of Temporal Events in Music -- 6.2.1.Tempo and Time Signature -- 6.2.2.Note Value -- 6.3.Onset Detection -- 6.3.1.Novelty Function -- 6.3.2.Peak Picking -- 6.3.3.Evaluation -- 6.4.Beat Histogram -- 6.4.1.Beat Histogram Features -- 6.5.Detection of Tempo and Beat Phase -- 6.6.Detection of Meter and Downbeat -- 7.1.Dynamic Time Warping -- 7.1.1.Example -- 7.1.2.Common Variants -- 7.1.3.Optimizations -- 7.2.Audio-to-Audio Alignment -- 7.2.1.Ground Truth Data for Evaluation -- 7.3.Audio-to-Score Alignment -- 7.3.1.Real-Time Systems M -- 7.3.2.Non-Real-Time Systems -- Contents note continued: 8.1.Musical Genre Classification -- 8.1.1.Musical Genre -- 8.1.2.Feature Extraction -- 8.1.3.Classification -- 8.2.Related Research Fields -- 8.2.1.Music Similarity Detection -- 8.2.2.Mood Classification -- 8.2.3.Instrument Recognition -- 9.1.Fingerprint Extraction -- 9.2.Fingerprint Matching -- 9.3.Fingerprinting System: Example -- 10.1.Musical Communication -- 10.1.1.Score -- 10.1.2.Music Performance -- 10.1.3.Production -- 10.1.4.Recipient -- 10.2.Music Performance Analysis -- 10.2.1.Analysis Data -- 10.2.2.Research Results -- A.1.Identity -- A.2.Commutativity -- A.3.Associativity -- A.4.Distributivity -- A.5.Circularity -- B.1.Properties of the Fourier Transformation -- B.1.1.Inverse Fourier Transform -- B.1.2.Superposition -- B.1.3.Convolution and Multiplication -- B.1.4.Parseval's Theorem -- B.1.5.Time and Frequency Shift -- B.1.6.Symmetry -- B.1.7.Time and Frequency Scaling -- B.1.8.Derivatives -- B.2.Spectrum of Example Time Domain Signals -- Contents note continued: B.2.1.Delta Function -- B.2.2.Constant -- B.2.3.Cosine -- B.2.4.Rectangular Window -- B.2.5.Delta Pulse -- B.3.Transformation of Sampled Time Signals -- B.4.Short Time Fourier Transform of Continuous Signals -- B.4.1.Window Functions -- B.5.Discrete Fourier Transform -- B.5.1.Window Functions -- B.5.2.Fast Fourier Transform -- C.1.Computation of the Transformation Matrix -- C.2.Interpretation of the Transformation Matrix -- D.1.Software Frameworks and Applications -- D.1.1.Marsyas -- D.1.2.CLAM -- D.1.3.jMIR -- D.1.4.CoMIRVA -- D.1.5.Sonic Visualiser -- D.2.Software Libraries and Toolboxes -- D.2.1.Feature Extraction -- D.2.2.Plugin Interfaces -- D.2.3.Other Software.
Restricted to subscribers or individual electronic text purchasers.
An easily accessible, hands-on approach to digital audio signal processingWith the proliferation of digital audio distribution over digital media, the amount of easily accessible music is ever-growing, requiring new tools for navigating, accessing, and retrieving music in meaningful ways. An understanding of audio content analysis is essential for the design of intelligent music information retrieval applications and content-adaptive audio processing systems.This book is about how to teach a computer to interpret music signals, thus allowing the design of tools for interacting with music. This book serves as a comprehensive guide on audio content analysis and how to apply it in signal processing and music informatics. Written by a well-known expert in the music industry, An Introduction to Audio Content Analysis ties together topics from audio signal processing and machine learning, showing how to use audio content analysis to pick up musical characteristics automatically. The author clearly explains the analysis of audio signals and the extraction of metadata describing the content of the signal, covering both abstract descriptions of technical properties and musical descriptions such as tempo, harmony and key, musical style, and performance attributes. Musical information is given a separate analysis in each category, whether tonal, pitch, harmony, key, temporal, or tempo, among others.Readers will get access to various analysis algorithms and learn to compare different standard approaches to the same task. The book includes a review of the fundamentals of audio signal processing, psychoacoustics, and music theory.An invaluable guide for newcomers to audio signal processing and industry experts alike, An Introduction to Audio Content Analysis also features downloadable MATLAB files from a companion website, www.AudioContentAnalysis.org, lists of abbreviations and symbols, and references.
Mode of access: World Wide Web
9781118393550
10.1002/9781118393550 doi
Content analysis (Communication)--Data processing.
Computational auditory scene analysis.
Computer sound processing.
Electronic books.
TK7881.4. / L47 2012eb
006.4/5
An introduction to audio content analysis : applications in signal processing and music informatics / Alexander Lerch. - 1 PDF (xxii, 248 pages).
Includes bibliographical references.
Machine generated contents note: 1.1.Audio Content -- 1.2.A Generalized Audio Content Analysis System -- 2.1.Audio Signals -- 2.1.1.Periodic Signals -- 2.1.2.Random Signals -- 2.1.3.Sampling and Quantization -- 2.1.4.Statistical Signal Description -- 2.2.Signal Processing -- 2.2.1.Convolution -- 2.2.2.Block-Based Processing -- 2.2.3.Fourier Transform -- 2.2.4.Constant Q Transform -- 2.2.5.Auditory Filterbanks -- 2.2.6.Correlation Function -- 2.2.7.Linear Prediction -- 3.1.Audio Pre-Processing -- 3.1.1.Down-Mixing -- 3.1.2.DC Removal -- 3.1.3.Normalization -- 3.1.4.Down-Sampling -- 3.1.5.Other Pre-Processing Options -- 3.2.Statistical Properties -- 3.2.1.Arithmetic Mean -- 3.2.2.Geometric Mean -- 3.2.3.Harmonic Mean -- 3.2.4.Generalized Mean -- 3.2.5.Centroid -- 3.2.6.Variance and Standard Deviation -- 3.2.7.Skewness -- 3.2.8.Kurtosis -- 3.2.9.Generalized Central Moments -- 3.2.10.Quantiles and Quantile Ranges -- 3.3.Spectral Shape -- 3.3.1.Spectral Rolloff -- Contents note continued: 3.3.2.Spectral Flux -- 3.3.3.Spectral Centroid -- 3.3.4.Spectral Spread -- 3.3.5.Spectral Decrease -- 3.3.6.Spectral Slope -- 3.3.7.Mel Frequency Cepstral Coefficients -- 3.4.Signal Properties -- 3.4.1.Tonalness -- 3.4.2.Autocorrelation Coefficients -- 3.4.3.Zero Crossing Rate -- 3.5.Feature Post-Processing -- 3.5.1.Derived Features -- 3.5.2.Normalization and Mapping -- 3.5.3.Subfeatures -- 3.5.4.Feature Dimensionality Reduction -- 4.1.Human Perception of Intensity and Loudness -- 4.2.Representation of Dynamics in Music -- 4.3.Features -- 4.3.1.Root Mean Square -- 4.4.Peak Envelope -- 4.5.Psycho-Acoustic Loudness Features -- 4.5.1.EBU R128 -- 5.1.Human Perception of Pitch -- 5.1.1.Pitch Scales -- 5.1.2.Chroma Perception -- 5.2.Representation of Pitch in Music -- 5.2.1.Pitch Classes and Names -- 5.2.2.Intervals -- 5.2.3.Root Note, Mode, and Key -- 5.2.4.Chords and Harmony -- 5.2.5.The Frequency of Musical Pitch -- 5.3.Fundamental Frequency Detection -- Contents note continued: 5.3.1.Detection Accuracy -- 5.3.2.Pre-Processing -- 5.3.3.Monophonic Input Signals -- 5.3.4.Polyphonic Input Signals -- 5.4.Tuning Frequency Estimation -- 5.5.Key Detection -- 5.5.1.Pitch Chroma -- 5.5.2.Key Recognition -- 5.6.Chord Recognition -- 6.1.Human Perception of Temporal Events -- 6.1.1.Onsets -- 6.1.2.Tempo and Meter -- 6.1.3.Rhythm -- 6.1.4.Timing -- 6.2.Representation of Temporal Events in Music -- 6.2.1.Tempo and Time Signature -- 6.2.2.Note Value -- 6.3.Onset Detection -- 6.3.1.Novelty Function -- 6.3.2.Peak Picking -- 6.3.3.Evaluation -- 6.4.Beat Histogram -- 6.4.1.Beat Histogram Features -- 6.5.Detection of Tempo and Beat Phase -- 6.6.Detection of Meter and Downbeat -- 7.1.Dynamic Time Warping -- 7.1.1.Example -- 7.1.2.Common Variants -- 7.1.3.Optimizations -- 7.2.Audio-to-Audio Alignment -- 7.2.1.Ground Truth Data for Evaluation -- 7.3.Audio-to-Score Alignment -- 7.3.1.Real-Time Systems M -- 7.3.2.Non-Real-Time Systems -- Contents note continued: 8.1.Musical Genre Classification -- 8.1.1.Musical Genre -- 8.1.2.Feature Extraction -- 8.1.3.Classification -- 8.2.Related Research Fields -- 8.2.1.Music Similarity Detection -- 8.2.2.Mood Classification -- 8.2.3.Instrument Recognition -- 9.1.Fingerprint Extraction -- 9.2.Fingerprint Matching -- 9.3.Fingerprinting System: Example -- 10.1.Musical Communication -- 10.1.1.Score -- 10.1.2.Music Performance -- 10.1.3.Production -- 10.1.4.Recipient -- 10.2.Music Performance Analysis -- 10.2.1.Analysis Data -- 10.2.2.Research Results -- A.1.Identity -- A.2.Commutativity -- A.3.Associativity -- A.4.Distributivity -- A.5.Circularity -- B.1.Properties of the Fourier Transformation -- B.1.1.Inverse Fourier Transform -- B.1.2.Superposition -- B.1.3.Convolution and Multiplication -- B.1.4.Parseval's Theorem -- B.1.5.Time and Frequency Shift -- B.1.6.Symmetry -- B.1.7.Time and Frequency Scaling -- B.1.8.Derivatives -- B.2.Spectrum of Example Time Domain Signals -- Contents note continued: B.2.1.Delta Function -- B.2.2.Constant -- B.2.3.Cosine -- B.2.4.Rectangular Window -- B.2.5.Delta Pulse -- B.3.Transformation of Sampled Time Signals -- B.4.Short Time Fourier Transform of Continuous Signals -- B.4.1.Window Functions -- B.5.Discrete Fourier Transform -- B.5.1.Window Functions -- B.5.2.Fast Fourier Transform -- C.1.Computation of the Transformation Matrix -- C.2.Interpretation of the Transformation Matrix -- D.1.Software Frameworks and Applications -- D.1.1.Marsyas -- D.1.2.CLAM -- D.1.3.jMIR -- D.1.4.CoMIRVA -- D.1.5.Sonic Visualiser -- D.2.Software Libraries and Toolboxes -- D.2.1.Feature Extraction -- D.2.2.Plugin Interfaces -- D.2.3.Other Software.
Restricted to subscribers or individual electronic text purchasers.
An easily accessible, hands-on approach to digital audio signal processingWith the proliferation of digital audio distribution over digital media, the amount of easily accessible music is ever-growing, requiring new tools for navigating, accessing, and retrieving music in meaningful ways. An understanding of audio content analysis is essential for the design of intelligent music information retrieval applications and content-adaptive audio processing systems.This book is about how to teach a computer to interpret music signals, thus allowing the design of tools for interacting with music. This book serves as a comprehensive guide on audio content analysis and how to apply it in signal processing and music informatics. Written by a well-known expert in the music industry, An Introduction to Audio Content Analysis ties together topics from audio signal processing and machine learning, showing how to use audio content analysis to pick up musical characteristics automatically. The author clearly explains the analysis of audio signals and the extraction of metadata describing the content of the signal, covering both abstract descriptions of technical properties and musical descriptions such as tempo, harmony and key, musical style, and performance attributes. Musical information is given a separate analysis in each category, whether tonal, pitch, harmony, key, temporal, or tempo, among others.Readers will get access to various analysis algorithms and learn to compare different standard approaches to the same task. The book includes a review of the fundamentals of audio signal processing, psychoacoustics, and music theory.An invaluable guide for newcomers to audio signal processing and industry experts alike, An Introduction to Audio Content Analysis also features downloadable MATLAB files from a companion website, www.AudioContentAnalysis.org, lists of abbreviations and symbols, and references.
Mode of access: World Wide Web
9781118393550
10.1002/9781118393550 doi
Content analysis (Communication)--Data processing.
Computational auditory scene analysis.
Computer sound processing.
Electronic books.
TK7881.4. / L47 2012eb
006.4/5