GB/T 45354.1-2025 Speech interaction technology for intelligent household appliances―Part 1: General requirements English, Anglais, Englisch, Inglés, えいご
This is a draft translation for reference among interesting stakeholders. The finalized translation (passing through draft translation, self-check, revision and verification) will be delivered upon being ordered.）
ICS 97.030
CCS Y 60
National Standards of the People's Republic of China
GB/T 45354.1-2025
Voice interaction technology for intelligent household appliances - Part 1: General requirements
智能家用电器的语音交互技术第1部分:通用要求
(English Translation)
Issue date: 2025-02-28 Implementation date: 2025-09-01
Issued by the State Administration for Market Regulation
the Standardization Administration of the People's Republic of China
Contents
Foreword
Introduction
1 Scope
2 Normative references
3 Terms and definitions
4 Classification of voice interaction of smart home appliances
5 Voice interaction framework structure
6 Technical requirements
7 Marks, Indications and Instructions for Use
8 Validation Method
Annex A (Normative) Special Requirements for Smart Home Appliances with Voice Interaction Function
Bibliography
Voice interaction technology for intelligent household appliances - Part 1: General requirements
1 Scope
This document specifies the voice interaction classification, voice interaction framework structure, voice interaction technical requirements, signs, instructions and instructions for use of smart household appliances (hereinafter referred to as "smart household appliances").
This document is applicable to the design, development, testing and evaluation of smart home appliances that interact by voice.
2 Normative references
The contents of the following documents constitute the essential provisions of this document through normative references in the text. Among them, for the referenced document with a date, only the version corresponding to that date is applicable to this document; The latest version of the undated referenced document (including all amendments) is applicable to this document.
GB/T 34145-2017 Chinese Speech Synthesis Internet Service Interface Specification
GB/T 37036.5-2023 Information technology-Biometric identification of mobile devices - Part 5: Voiceprint
GB/T 41807 Information security technology voiceprint identification data security requirements
SJ/T 11540-20153 General specification for chemically safe active loudspeakers
3 Terms and definitions, abbreviations
3.1 Terms and attributes
following terms and definitions apply to this document
3.1
voice interaction speech interaction
information transmission and communication activities between humans and functional units through speech
3.2
speech recognition
process of transforming human sound signals into words or instructions
3.3
speech synthesis
process of synthesizing human language by mechanical, electronic means..
3.4
voice service platform speech service platform
platform that provides one or more services such as speech recognition, semantic understanding, speech interaction decision-making, and speech synthesis for smart home appliances
3.5
smart home appliance service platform intelligent household appliances service platform
platform that provides services, management and interconnection for smart home appliances, and at the same time provides access services between smart home appliances and other home appliances, other industries or third-party applications
3.6
sound source localization acoustic source localization
process of judging the position of the sound-producing object
3.7
semantic understanding semantic understanding
Make the functional unit understand the intention of a person speaking
3.8
voice wake-up speech wake-up; voice trigger
voice interaction system in the audio stream monitoring state switches to other processing states such as command word recognition and continuous voice recognition after detecting the occurrence of specific features or events
3.9
voiceprint recognition voiceprint recognition
process of recognizing the speaker corresponding to the speech segment according to the voiceprint feature of the speech to be recognized
3.10
voice interruption speech interruption
in the process of playing sound, when the voice acquisition device detects valid voice input, the voice interaction system goes to other processing processes such as voice recognition
3.11
sound pressure level
base 10 logarithm of the ratio of the time mean square of the sound pressure signal to the square of the reference value is multiplied by 10.
3.12
semantic rejection semantic rejection
ability to perform semantic analysis and rejection of unprocessable or invalid speech input content.
4 Classification of voice interaction of smart home appliances
4.1 Classification according to whether it is networked or not
According to whether the voice interaction function needs to be networked, it is divided into:
a) in-line;
b) offline type;
c) Offline/online hybrid
4.2 Classification by pickup distance
According to the pickup distance, it is divided into:
a) Near field: pickup distance ≤ 1 m;
b) midfield: 1m < pickup distance ≤ 3m;
c) far field: 3m < pickup distance ≤ 5m;
d) Ultra far field: pickup distance > 5m.
4.3 Classification by whether wake-up is needed
According to whether the voice interaction function needs to wake up, it is divided into:
a) no wake-up;
b) Need to wake up:
——Voice wake-up;
——Other non-voice wake-up methods.
Examples: wake-up by key, wake-up by gesture, wake-up by system call.
5 Speech interaction framework knot
See Figure 1 for the schematic diagram of the voice interaction framework structure of smart home appliances
