Table of Contents - F.746.25 (04/2026) - Framework and functional requirements for voice interaction of in-vehicle multimodal system

1	Scope
2	References
3	Definitions
	3.1	Terms defined elsewhere
	3.2	Terms defined in this Recommendation
4	Abbreviations and acronyms
5	Conventions
6	Overview of voice interaction of in-vehicle multimodal system
	6.1	Background
	6.2	General scenarios
7	Framework for voice interaction of in-vehicle multimodal system
8	Functional requirements for voice interaction of in-vehicle multimodal system
	8.1	Requirements for data preprocessing function
	8.2	Requirements for audio-visual engine function
	8.3 	Requirements for multimodal recognition function
	8.4	Requirements for voice interaction function
9	Workflow of multimodal functions for voice interaction
	9.1	Workflow preview
	9.2	Workflow of multimodal speech separation
	9.3 	Workflow of multimodal wake-up
	9.4	Workflow of multimodal VAD
	9.5	Workflow of multimodal NLU
10	Reference points for framework of voice interaction
	10.1	Reference point RP1
	10.2	Reference point RP2
	10.3	Reference point RP3
	10.4	Reference point RP4
Appendix I
	I.1	Implementation example for multimodal speech separation
	I.2 	Implementation example for multimodal VAD running on an AI chip
Bibliography