GB/T 41813.1-2022Information technology—Intelligent speech interaction testing method—Part 1: Speech recognition (English PDF)
信息技术 智能语音交互测试方法 第1部分:语音识别
This is a limited preview
Buy now to download the full PDF (15 pages)
Need quotation for your management?
Get a formal quotation for GB/T 41813.1-2022 in 30 minutes.
Issued by
SAMR; SAC
Level / Type
National · Recommended
Issue date
October 14, 2022
Implementation date
May 1, 2023
Scope
GB/T 41813.1-2022 is the English-translated version of 信息技术 智能语音交互测试方法 第1部分:语音识别.
GB/T 41813.1-2022 is the test method for the speech recognition part of intelligent voice interaction systems.
Its contents list covers test preparation and execution - the test dataset, test tools, test equipment, test environment and the recording of results - then functional tests for voice signal collection, speech-to-text, voice wake-up, front-end signal processing, speaker separation, language information recognition and post-processing, and performance tests for recognition effect and efficiency, wake-up effect, speaker separation and system stability.
Clause 1 applies it to tests designed and run by speech service providers, users and third-party testing bodies. Its introduction states that GB/T 41813 provides general test methods for the GB/T 36464 series and that its other parts cover semantic understanding and speech synthesis. Issued on 14 October 2022, it has applied since 1 May 2023.
Found what you need?
Document preview — GB/T 41813.1-2022
National Standard of the People's Republic of China
- ICS
- 35.240.01
- Classification
- L 77
Issued by: State Administration for Market Regulation; Standardization Administration of the PRC
Contents
- Preface
- Introduction
- 1 Scope
- 2 Normative references
- 3 Terms and Definitions
- 4 Overview
- 5 Test Preparation and Execution
- 5.1 Test dataset
- 5.2 Test Tools
- 5.3 Test equipment
- 5.4 Test Environment
- 5.5 Test execution
- 5.6 Test Results
- 6 Functional Test Method
- 6.1 Voice Signal Collection
- 6.2 Speech to text
- 6.3 Voice wakeup
- 6.4 Front-End Signal Processing
- 6.5 Speaker Separation
- 6.6 Language Information Recognition
- 6.7 Post-processing of speech recognition
- 7 Performance Test Method
- 7.1 Speech recognition effect
- 7.2 Speech Recognition Efficiency
- 7.3 Voice wake-up effect
- 7.4 Front-end signal processing effects
- 7.5 Speaker separation effect
- 7.6 The effect of language information recognition
- 7.7 System stability
- Reference
Foreword
This document is in accordance with the provisions of GB/T 1.1-2020 "Guidelines for Standardization Work Part 1: Structure and Drafting Rules of Standardization Documents" drafted.
This document is the first part of GB/T 41813 "Information Technology Intelligent Voice Interaction Test Method". GB/T 41813 has been released the following parts.
--- Part 1: Speech recognition;
--- Part 2: Semantic understanding.
Introduction
Intelligent voice interaction is used in smart home, smart customer service, mobile terminals, vehicle terminals, as well as smart education, smart medical care, smart office, and services.
It is widely used in many fields such as robotics, and has become one of the important ways of human-computer interaction. With the deepening of intelligent voice interaction In all aspects of production and life, it is necessary to unify the system reference framework, basic technical requirements, and Internet interface requirements of intelligent voice interaction. a specification. In this regard, the country has formulated the basic national standards to support the intelligent voice interaction system. On this basis, it is also necessary to use the A test method and evaluation standard to evaluate the ability of intelligent voice interaction system, for intelligent voice interaction related products and services Provide the basic method and basis for evaluation.
GB/T 41813 "Information Technology Intelligent Voice Interaction Test Method" is GB/T 36464 (all parts) "Information Technology Intelligent Language Audio Interaction System" provides basic and general testing methods. Intelligent voice interaction includes three basic loops. speech recognition, semantic understanding and speech synthesis.
The test objects, test items, test environments and test methods involved in each link are different. GB/T 41813 "Information Technology Intelligent Voice Interaction Test Methods" aims to establish and describe general test items and general test methods applicable to all aspects of intelligent voice interaction. It consists of three parts.
--- Part 1: Speech recognition. The purpose is to provide general test items and common test items for speech recognition in intelligent voice interaction applications. using the test method.
--- Part 2: Semantic understanding. The purpose is to provide general test items and common test items for semantic understanding in intelligent voice interaction applications. using the test method.
--- Part 3: Speech synthesis. The purpose is to provide general test items and common test items for speech synthesis in intelligent voice interaction applications. using the test method.
1 Scope
This document describes the general test items and general test methods for speech recognition systems in intelligent voice interaction testing.
This document applies to speech recognition systems for intelligent speech interaction applications by intelligent speech service providers, users and third-party testing agencies Design and implementation of tests.
2 Normative references
The contents of the following documents constitute essential provisions of this document through normative references in the text. Among them, dated citations documents, only the version corresponding to that date applies to this document; for undated references, the latest edition (including all amendments) applies to this document.
GB/T 21023 General Technical Specification for Chinese Speech Recognition System
GB/T 36464 (all parts) Information technology intelligent voice interactive system
3 Terms and Definitions
The terms and definitions defined in GB/T 36464 (all parts) and the following terms and definitions apply to this document.
3.1 Speech recognition
The process of converting human voice signals into words or instructions. [Source: GB/T 36464.1-2020, 3.7]
3.2 Speakerdiarization
The process of speaker segmentation and speaker clustering for multiple speakers in an audio stream containing valid speech signals.
NOTE: The purpose of speaker separation is generally to classify and track multiple speakers present in space.
3.3 Speaker segmentation
Find out the temporal boundaries of speaker changes among multiple speakers, and split the audio stream into multiple speech segments according to these boundaries.
3.4 Speaker clustering
Categorize one or more speech segments belonging to the same speaker.
3.5 Speech coding
speechcoding; speechchencoding speechwaveformcoding According to a set of plans that can reasonably reconstruct the speech signal, the transformation from the digitized speech signal to a discrete sequence of data elements.
NOTE: Speech digitization can be combined with a coding for speech compression. Therefore, the term "voice coding" often refers to such combinatorial operations. [Source: GB/T 5271.29-2006, 29.01.23]
......
This preview omits tables, figures, formulas and parts of the technical clauses. The complete document — 15 pages — is available in the English PDF.
Referenced standards
Similar standards
How to Download GB/T 41813.1-2022
- 1
Add to cart
Click "Download PDF" on this page and choose "Buy this standard". You can add more standards before checkout.
- 2
Checkout
Enter your email and billing details. Payment is processed securely by Stripe (cards or bank transfer). Prefer bank details? Request a quotation (min. order $300).
- 3
Fast delivery
After payment you'll receive an email confirmation. The English PDF is sent to the same address, usually within minutes and at the latest within 1 business day.
- 4
Invoice included
A tax invoice is attached to the confirmation email. Need a custom invoice? Contact us.
Related Standards
GB/T 21023-2007 — Chinese speech recognition system common technical specifications
GB/T 36464.1-2020 — Information technology - Intelligent speech interaction system - Part 1: General specifications
GB/T 36464.2-2018 — Information technology—Intelligent speech interaction system—Part 2: Intelligent home appliances
GB/T 41813.1-2022
$240.00