Muutke küpsiste eelistusi

E-raamat: Intelligent Music Production [Taylor & Francis e-raamat]

(Digital Media Technology Lab, Birmingham City University), , (Centre for Digital Music, Queen Mary University of London)
  • Formaat: 218 pages, 8 Tables, black and white; 39 Line drawings, black and white; 17 Halftones, black and white
  • Sari: Audio Engineering Society Presents
  • Ilmumisaeg: 25-Oct-2019
  • Kirjastus: CRC Press
  • ISBN-13: 9781315166100
  • Taylor & Francis e-raamat
  • Hind: 189,26 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
  • Tavahind: 270,37 €
  • Säästad 30%
  • Formaat: 218 pages, 8 Tables, black and white; 39 Line drawings, black and white; 17 Halftones, black and white
  • Sari: Audio Engineering Society Presents
  • Ilmumisaeg: 25-Oct-2019
  • Kirjastus: CRC Press
  • ISBN-13: 9781315166100

In audio engineering, whether for broadcast, live sound, games or film, one typically has many different recordings of sound sources (vocals, sound effects, wind instruments, etc.), each one represented on a separate track. These tracks need to be heard simultaneously in the final audio mixture. Each track may have been created in a different way, in a unique environment, at a different loudness level than other tracks. Some tracks may mask each other, some may be too loud or too quiet, some may blend in well with the others most of the time, but then have periods where they sound terrible. The ways in which a sound engineer solves these problems can vary based on the individual, making it a difficult problem to model. Audio production is still very time consuming, and requires a complex set of creative and technical skills. Furthermore, there is a lack of fundamental understanding of how we perceive mixed audio content, and what user preferences might be for different production styles. In this book, we provide insight into these areas of ambiguity, and attempt to provide computational models of these inherently complex subjective processes.

In related domains such as image and video production, a plethora of tools including autofocus, face detection, context-aware editing and red eye removal provide intuitive and simple ways to manipulate and interact with content, however intelligent system in audio production tend to be less prominent in commercially released hardware and software. Commercially available audio editing devices are essentially deaf, they tend not ‘listen’ to the incoming audio, and have no knowledge of the sound scene or of preferred production techniques. Researchers today aim to change that situation, making systems able to ‘listen’ to the audio and suggest or even perform steps to improve mixing and mastering. In this book we detail the state of the art in intelligent music production systems, ranging from systems for semantic control of audio processing tools, to semi- and fully-automated mixing and mastering systems.

This book brings together both published and unpublished work in the field of audio and presents a range of academic research projects in an understandable and usable format. Readers of the book will be provided with a range of demos and examples, including a repository of links, code snippets and software tools for incorporation of the techniques into their workflow.

List of Figures xii
List of Tables xiv
Preface xv
Acknowledgments xvi
Part I What Do We Already Know? 1(44)
1 Introduction
3(13)
1.1 Intelligent Music Production - An Emerging Field
3(1)
1.2 Scope
4(1)
1.2.1 Intelligent
4(1)
1.2.2 Music
5(1)
1.2.3 Production
5(1)
1.3 Motivation and Justification
5(3)
1.3.1 Camera Comparison and the 'Instamix'
7(1)
1.3.2 Sound on Sound
7(1)
1.3.3 Aims and Objectives
7(1)
1.4 History of the Field
8(5)
1.4.1 Early Automation in Audio Effects
8(1)
1.4.2 Automatic Microphone Mixing
9(2)
1.4.3 Steps Towards Intelligent Systems
11(1)
1.4.4 The Automatic Mixing Revolution
11(2)
1.5 Applications and Impact
13(3)
1.5.1 Intelligent Assistants
13(1)
1.5.2 Black Box
14(1)
1.5.3 Interfaces
14(1)
1.5.4 Metering and Diagnostics
15(1)
1.5.5 Interactive Audio
15(1)
2 Understanding Audio Effects
16(19)
2.1 Fundamental Properties
16(2)
2.2 Audio Effect Classification
18(6)
2.2.1 Classification by Perception
18(2)
2.2.2 Classification by Technique
20(1)
2.2.3 Classification by Control
20(4)
2.3 Traditional Audio Effects
24(11)
2.3.1 Balance
24(1)
2.3.2 Stereo Positioning
24(1)
2.3.3 Equalization
25(2)
2.3.4 Compression
27(1)
2.3.5 Expanders and Noise Gates
28(1)
2.3.6 Time Alignment
29(3)
2.3.7 Reverb
32(1)
2.3.8 Distortion
33(2)
3 Understanding the Mix
35(10)
3.1 Fundamentals and Concepts
35(4)
3.1.1 Terminology
35(2)
3.1.2 The Role of the Mix Engineer
37(1)
3.1.3 The Mixing Workflow
37(1)
3.1.4 The Stage Metaphor
38(1)
3.1.5 Order of Processes
39(1)
3.2 Mix Assumptions
39(3)
3.2.1 Live Versus Pre-recorded
40(1)
3.2.2 Venue Acoustics
41(1)
3.2.3 Static Versus Time Varying Mix
41(1)
3.3 Challenges
42(5)
3.3.1 Cultural Influence
42(1)
3.3.2 Effect of Experience
42(1)
3.3.3 Genre
42(1)
3.3.4 Approaches and Subjectivity
43(2)
Part II How Do We Construct Intelligent Structures? 45(50)
4 IMP Construction
47(16)
4.1 Intelligent and Adaptive Digital Audio Effects
47(1)
4.2 Building Blocks of Intelligent Audio Effects
48(3)
4.2.1 Feature Extraction
48(1)
4.2.2 Feature Extraction with Noise
49(1)
4.2.3 Side-chain Processing
50(1)
4.3 Cross-adaptive Processing
51(1)
4.4 Mixing Systems
52(1)
4.5 Automatic Mixing Systems
53(1)
4.6 Building Blocks of Automatic Mixing Tools
54(3)
4.6.1 Reference Signals and Adaptive Thresholds
56(1)
4.6.2 System Stability
57(1)
4.6.3 Live Processing
57(1)
4.7 Intelligence
57(5)
4.7.1 Automated, Automatic, Autonomous
57(1)
4.7.2 Incorporating Best Practices into Constrained Control Rules
58(4)
4.8 Concluding Remarks
62(1)
5 Data Collection and Representation
63(20)
5.1 Datasets
64(8)
5.1.1 Multitrack Audio
64(2)
5.1.2 Open Multitrack Testbed
66(2)
5.1.3 Audio Processing Data
68(2)
5.1.4 Other Notable Datasets
70(2)
5.2 Data Collection Methods
72(4)
5.2.1 In the DAW
72(1)
5.2.2 Via the Web
73(3)
5.3 Data Representation
76(7)
5.3.1 Formats
76(3)
5.3.2 Ontologies and Knowledge Representation
79(2)
5.3.3 Licenses
81(2)
6 Perceptual Evaluation in Music Production
83(12)
6.1 Basic Principles
84(1)
6.2 Subject Selection and Surveys
84(1)
6.3 Stimulus Presentation
85(3)
6.3.1 Pairwise or Multiple Stimuli
85(1)
6.3.2 To MUSHRA or not to MUSHRA
85(2)
6.3.3 Free Switching and Time-aligned Stimuli
87(1)
6.4 Response Format
88(2)
6.4.1 Discrete and Continuous Rating and Ranking
88(1)
6.4.2 Rating Scale Names
89(1)
6.4.3 Comments
89(1)
6.4.4 Method of Adjustment Tests
90(1)
6.5 Set-up
90(2)
6.5.1 Headphones or Speakers
90(1)
6.5.2 Listening Environment
90(1)
6.5.3 Listening Level
91(1)
6.5.4 Visual Distractions
91(1)
6.5.5 Online Tests
91(1)
6.6 Perceptual Evaluation of Mixing Systems
92(3)
Part III How Do We Perform Intelligent Music Production? 95(78)
7 IMP Systems
97(18)
7.1 Level Balance
97(3)
7.1.1 Balance Assumptions
97(2)
7.1.2 Intelligent Multitrack Faders
99(1)
7.2 Stereo Panning
100(1)
7.2.1 Panning Assumptions
100(1)
7.2.2 Intelligent Multitrack Panning
101(1)
7.3 Equalization
101(3)
7.3.1 EQ Assumptions
101(1)
7.3.2 Intelligent Single Track Equalizers
102(1)
7.3.3 Intelligent Multitrack Equalizers
103(1)
7.4 Dynamic Range Compression
104(3)
7.4.1 Dynamic Range Compression Assumptions
104(1)
7.4.2 Intelligent Single Track Compressors
105(1)
7.4.3 Intelligent Multitrack Compressors
106(1)
7.5 Reverb
107(2)
7.5.1 Reverb Assumptions
107(1)
7.5.2 Intelligent Single Track Reverb
108(1)
7.6 Distortion
109(5)
7.6.1 Distortion Amount Automation
109(3)
7.6.2 Subjective Evaluation
112(1)
7.6.3 Adaptive Anti-aliasing
113(1)
7.6.4 Other Automation
113(1)
7.7 Instrument-specific Processing and Multi-effect Systems
114(1)
8 IMP Processes
115(18)
8.1 Fundamentals and Concepts
115(1)
8.2 Editing
116(7)
8.2.1 Automatic Take Selection
116(1)
8.2.2 Structural Segmentation
116(1)
8.2.3 Time Alignment
116(2)
8.2.4 Polarity Correction
118(1)
8.2.5 Noise Gates
118(2)
8.2.6 Unmasking
120(2)
8.2.7 Microphone Artifacts
122(1)
8.3 Humanization
123(2)
8.3.1 Isolated Sequences
123(1)
8.3.2 Multitrack Sequences
124(1)
8.4 Workflow Automation
125(4)
8.4.1 Subgrouping
125(3)
8.4.2 Processing Chain Recommendation
128(1)
8.4.3 Copying Mix Layout
129(1)
8.5 Live Sound Reinforcement
129(1)
8.5.1 Feedback Prevention
129(1)
8.5.2 Monitor Mixing
130(1)
8.6 Reverse Audio Engineering
130(3)
9 IMP Interfaces
133(33)
9.1 Fundamentals and Concepts
134(5)
9.1.1 Skeuomorphism
134(1)
9.1.2 Automation
135(1)
9.1.3 Mapping Strategies
135(2)
9.1.4 Dimensionality Reduction
137(2)
9.2 Abstract Control
139(14)
9.2.1 Beyond the Channel Strip
139(6)
9.2.2 Digital Audio Effects
145(1)
9.2.3 Metering
146(2)
9.2.4 Gestural Control
148(4)
9.2.5 Haptics and Auditory Displays
152(1)
9.3 Natural Language
153(13)
9.3.1 A Shared Vocabulary
153(3)
9.3.2 Term Categorization
156(2)
9.3.3 Agreement Measures
158(2)
9.3.4 Similarity Measures
160(4)
9.3.5 Semantic Audio Processing
164(2)
10 Future Work
166(7)
10.1 Conclusions
166(1)
10.2 What We Have Covered
167(1)
10.3 Future Directions
168(3)
10.3.1 Data Availability
168(1)
10.3.2 Multitrack Audio Effects
169(1)
10.3.3 Mixing for Hearing Loss
169(1)
10.3.4 Interactive Audio
170(1)
10.3.5 Turing Test
171(1)
10.4 Final Thoughts
171(2)
Appendix A Additional Resources 173(8)
Intelligent Sound Engineering Blog
173(1)
Intelligent Sound Engineering YouTube Channel
173(1)
Interactive Audio Lab
174(1)
Web Audio Evaluation Tool
174(1)
The SAFE Dataset
174(1)
Stems
174(1)
HDFS
174(7)
Bibliography 181(18)
Index 199
Brecht De Man is cofounder of Semantic Audio Labs and previously worked at Queen Mary University of London and Birmingham City University. He has published, presented and patented research on analysis of music production practices, audio effect design and perception in sound engineering.

Ryan Stables is an Associate Professor of Digital Audio Processing at the Digital Media Technology Lab at Birmingham City University, and cofounder of Semantic Audio Labs.

Joshua D. Reiss is a Professor of Audio Engineering at the Centre for Digital Music at Queen Mary University of London.