IEEE 3302-2022

$60.67

IEEE Standard Adoption of Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) Technical Specification Context-based Audio Enhanced (CAE) Version 1.4 (Published)

Published By	Publication Date	Number of Pages
IEEE	2022	94

Guaranteed Safe Checkout

Category: IEEE

If you have any questions, feel free to reach out to our online customer service team by clicking on the bottom right corner. We’re here to assist you 24/7.
Email:[email protected]

Description

New IEEE Standard – Active. This standard adopts MPAI Technical Specification Version 1.4 as an IEEE Standard. The Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) Technical Specification Context-based Audio Enhancement (CAE) Version 1.4 is a collection of four use cases specifying AI-based technologies for audio-related applications including entertainment, communication, post-production, teleconferencing, and restoration.

PDF Catalog

PDF Pages	PDF Title
1	IEEE Std 3302™-2022 Front Cover
2	Title page
4	Important Notices and Disclaimers Concerning IEEE Standards Documents
8	Paticipants
9	Introduction
10	Specification for MPAI-CAE
11	Contents
13	1 Introduction (Informative)
14	2 Scope of standard
15	2.1 Emotion-Enhanced Speech (EES) 2.2 Audio Recording Preservation (ARP) 2.3 Speech Restoration System (SRS) 2.4 Enhanced Audioconference Experience (EAE)
16	2.5 Normative content of the Use Cases 3 Terms and Definitions
18	4 References 4.1 Normative References
19	4.2 Informative References 5 Use Case Architectures 5.1 Emotion-Enhanced Speech (EES) 5.1.1 Scope of Use Case 5.1.2 I/O data
20	5.1.3 Implementation Architecture 5.1.4 AI Modules
21	5.2 Audio Recording Preservation (ARP) 5.2.1 Scope of Use Case 5.2.2 I/O data 5.2.3 Implementation Architecture
23	5.2.4 AI Modules 5.3 Speech Restoration System (SRS) 5.3.1 Scope of Use Case
24	5.3.2 I/O Data 5.3.3 Implementation Architecture
25	5.3.4 AI Modules 5.4 Enhanced Audioconference Experience (EAE) 5.4.1 Scope of Use Case
26	5.4.2 I/O data 5.4.3 Implementation Architecture
27	5.4.4 AI Modules
28	6 AIMs 6.1 AIM Interoperability 6.2 AIMs and their data 6.2.1 Emotion Enhanced Speech 6.2.2 Audio Recording Preservation (ARP)
29	6.2.3 Speech Restoration System (SRS) 6.2.4 Enhanced Audioconference Experience (EAE) 6.3 Data Formats
30	6.3.1 Access Copy Files 6.3.2 Audio Scene Geometry 6.3.2.1 Syntax
31	6.3.2.2 Semantics
32	6.3.3 Damaged List 6.3.3.1 Syntax 6.3.3.2 Semantics 6.3.4 Denoised Speech
33	6.3.5 Editing List 6.3.5.1 Syntax
34	6.3.5.2 Semantics
35	6.3.6 Emotion 6.3.6.1 Syntax 6.3.6.2 Semantics
39	6.3.7 Emotionless Speech 6.3.8 Interleaved Multichannel Audio 6.3.9 Irregularity File 6.3.9.1 Syntax
40	6.3.9.2 Semantics
42	6.3.10 Irregularity Image 6.3.11 Microphone Array Audio 6.3.12 Microphone Array Geometry 6.3.12.1 Syntax
43	6.3.12.2 Semantics
44	6.3.13 Mode Selection
45	6.3.14 Multichannel Audio Stream 6.3.15 Neural Network Speech Model
46	6.3.16 Preservation Audio File 6.3.17 Preservation Audio-Visual File 6.3.18 Preservation Master Files 6.3.19 Source Dictionary 6.3.20 Source Model KB Query Format 6.3.21 Speech Features
47	6.3.21.1 Semantics
48	6.3.22 Spherical Harmonic Decomposition 6.3.23 Transform Denoised Speech 6.3.24 Transform Speech
49	6.3.25 Transform Multichannel Audio 6.3.26 Video
50	Annex 1 MPAI-wide terms and definitions
53	Annex 2 Notices and Disclaimers Concerning MPAI Standards (Informative)
55	Annex 3 Patent Declarations
56	Annex 4 Examples (Informative) A4.1 Audio Scene Geometry A4.2 Damaged List A4.3 Editing List
57	A4.4 Irregularity File
58	A4.5 Microphone Array Geometry
59	A4.6 Speech Features 1 A4.7 Speech Features 2
60	Annex 5 AIW and AIM Metadata of CAE-EES A5.1 AIW Metadata
62	A5.2 AIM Metadata A5.2.1 Speech Feature Analyser1
63	A5.2.2 Speech Feature Analyser2
64	A5.2.3 Emotion Feature Producer
65	A5.2.4 Emotion Inserter1 A5.2.5 Emotion Inserter2
67	Annex 6 AIW and AIM Metadata of CAE-ARP A6.1 AIW metadata
71	A6.2 AIM metadata A6.2.1 Audio Analyser
72	A6.2.2 Video Analyser
73	A6.2.3 Tape Irregularity classifier
74	A6.2.4 Tape Audio Restoration
75	A6.2.5 Packager
77	Annex 7 AIW and AIM Metadata of CAE-SRS A7.1 AIW metadata
79	A7.2 AIM metadata A7.2.1 Speech Model Creation A7.2.2 Speech Synthesiser
80	A7.2.3 Assembler
82	Annex 8 AIW and AIM Metadata of CAE-EAE A8.1 AIW Metadata
87	A8.2 AIM Metadata A8.2.1 Analysis Transform
88	A8.2.2 Sound Field Description
89	A8.2.3 Speech Detection and Separation
90	A8.2.4 Noise Cancellation
91	A8.2.5 Synthesis Transform
92	A8.2.6 Packager
94	Back Cover

Additional information

Standard Title	IEEE Standard Adoption of Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) Technical Specification Context-based Audio Enhanced (CAE) Version 1.4 (Published)
Published Code	IEEE
Publication Date	2022
Pages Count	94

Preview PDF


PDF Format	Searchable	Printable	Preview Now

IEEE 3302-2022

PDF Catalog

Related products