1、Information technology User interfaces Voice commands Part 2: Constructing and testing BS ISO/IEC 30122-2:2017 BSI Standards Publication WB11885_BSI_StandardCovs_2013_AW.indd 1 15/05/2013 15:06National foreword This British Standard is the UK implementation of ISO/IEC 30122-2:2017. The UK participat
2、ion in its preparation was entrusted to Technical Committee ICT/-/6, ICT Accessibility. A list of organizations represented on this committee can be obtained on request to its secretary. This publication does not purport to include all the necessary provisions of a contract. Users are responsible fo
3、r its correct application. The British Standards Institution 2017. Published by BSI Standards Limited 2017 ISBN 978 0 580 81359 7 ICS 35.240.20 Compliance with a British Standard cannot confer immunity from legal obligations. This British Standard was published under the authority of the Standards P
4、olicy and Strategy Committee on 28 February 2017. Amendments/corrigenda issued since publication Date Text affected BRITISH STANDARD BS ISO/IEC 30122-2:2017Information technology User interfaces Voice commands Part 2: Constructing and testing Technologies de linformation Interfaces utilisateurs Comm
5、andes vocales Partie 2: Construire et tester INTERNATIONAL STANDARD ISO/IEC 30122-2 Reference number ISO/IEC 30122-2:2017(E) First edition 2017-02 ISO/IEC 2017 BS ISO/IEC 30122-2:2017 ii ISO/IEC 2017 All rights reserved COPYRIGHT PROTECTED DOCUMENT ISO/IEC 2017, Published in Switzerland All rights r
6、eserved. Unless otherwise specified, no part of this publication may be reproduced or utilized otherwise in any form or by any means, electronic or mechanical, including photocopying, or posting on the internet or an intranet, without prior written permission. Permission can be requested from either
7、 ISO at the address below or ISOs member body in the country of the requester. ISO copyright office Ch. de Blandonnet 8 CP 401 CH-1214 Vernier, Geneva, Switzerland Tel. +41 22 749 01 11 Fax +41 22 749 09 47 copyrightiso.org www.iso.org ISO/IEC 30122-2:2017(E) BS ISO/IEC 30122-2:2017 ISO/IEC 30122-2:
8、2017(E)Foreword iv Introduction v 1 Scope . 1 2 Normative references 1 3 T erms and definitions . 1 4 Conformity 2 5 Requirements and recommendations 2 5.1 General . 2 5.2 Phonetics of phrase for a voice command . 2 5.3 Design principle for a voice command . 2 5.3.1 Phonetic description of words . 2
9、 5.3.2 Ease of pronunciation 2 5.3.3 Variation of pronunciation 2 5.4 Test of speech recognition engine 3 5.4.1 General 3 5.4.2 Subject. 3 5.4.3 Samples of a voice command 3 5.4.4 Conditions of test . 3 5.4.5 Procedure of test 3 5.4.6 Results . 4 Bibliography 5 ISO/IEC 2017 All rights reserved iii C
10、ontents Page BS ISO/IEC 30122-2:2017 ISO/IEC 30122-2:2017(E) Foreword ISO (the International Organization for Standardization) and IEC (the International Electrotechnical Commission) form the specialized system for worldwide standardization. National bodies that are members of ISO or IEC participate
11、 in the development of International Standards through technical committees established by the respective organization to deal with particular fields of technical activity. ISO and IEC technical committees collaborate in fields of mutual interest. Other international organizations, governmental and
12、non-governmental, in liaison with ISO and IEC, also take part in the work. In the field of information technology, ISO and IEC have established a joint technical committee, ISO/IEC JTC 1. The procedures used to develop this document and those intended for its further maintenance are described in the
13、 ISO/IEC Directives, Part 1. In particular the different approval criteria needed for the different types of ISO documents should be noted. This document was drafted in accordance with the editorial rules of the ISO/IEC Directives, Part 2 (see www .iso .org/ directives). Attention is drawn to the po
14、ssibility that some of the elements of this document may be the subject of patent rights. ISO shall not be held responsible for identifying any or all such patent rights. Details of any patent rights identified during the development of the document will be in the Introduction and/or on the ISO list
15、 of patent declarations received (see www .iso .org/ patents). Any trade name used in this document is information given for the convenience of users and does not constitute an endorsement. For an explanation on the meaning of ISO specific terms and expressions related to conformit y assessment, as
16、well as information about ISOs adherence to the World Trade Organization (WTO) principles in the Technical Barriers to Trade (TBT) see the following URL: www . i s o .org/ iso/ foreword .html. The committee responsible for this document is ISO/IEC JTC 1, Information technology, Subcommittee SC 35, U
17、ser interfaces. A list of all parts in the ISO/IEC 30122 series can be found on the ISO website.iv ISO/IEC 2017 All rights reserved BS ISO/IEC 30122-2:2017 ISO/IEC 30122-2:2017(E) Introduction Voice command is used for controlling ICT devices with the voice and in the language of the user. This tech
18、nology is based on speech recognition, with some consideration for language tolerance (different accents or speech impairment while using a given language). It is also beneficial to the people who are operating the ICT device when/where they cannot use hands or fingers to operate it. This document d
19、efines the principal standardized voice commands that will be commonly used in various ICT devices. ISO/IEC 2017 All rights reserved v BS ISO/IEC 30122-2:2017 Information technology User interfaces Voice commands Part 2: Constructing and testing 1 Scope This document provides the technical criterion
20、s and test methods of voice commands and its speech recognition engine. The technical criterions include the phonetic requirements for spoken words or phrases that compose the voice command. The test methods verify whether the voice command or speech recognition engine satisfies the required specifi
21、cations. 2 Normative references There are no normative references in this document. 3 T erms a nd definiti ons For the purposes of this document, the following terms and definitions apply. ISO and IEC maintain terminological databases for use in standardization at the following addresses: IEC Electr
22、opedia: available at h t t p :/ www .electropedia .org/ ISO Online browsing platform: available at h t t p :/ www .iso .org/ obp 3.1 word smallest linguistic unit conveying a specific meaning SOURCE: ISO 5127:2001, 1.1.2.07, modified 3.2 syllable segment of speech which consists of a vowel with or w
23、ithout one or more accompanying consonants immediately preceding or following SOURCE: ISO 8253-3:2012, 3.8 3.3 sentence related group of word forms containing a predication, usually expressing a complete thought and forming the basic unit of discourse structure SOURCE: ISO 24615-1:2014, 3.15 INTERNA
24、TIONAL ST ANDARD ISO/IEC 30122-2:2017(E) ISO/IEC 2017 All rights reserved 1 BS ISO/IEC 30122-2:2017 ISO/IEC 30122-2:2017(E) 3.4 speech recognition conversion, by a functional unit, of a speech signal to a representation of the content of the speech SOURCE: ISO/IEC 2382:2015, 2120735, modified 4 Conf
25、ormity The voice command is conformant to this document if it meets all of the requirements of Clause 5. 5 Requirements and recommendations 5.1 General Words or phrases for voice commands shall be recognized correctly. Therefore, the following conditions are considered. Words or phrases for voice co
26、mmands are recognized easily. Acoustically similar words or phrases are not registered. Words or phrases that waver depending on the individual are not used. 5.2 Phonetics of phrase for a voice command The voice command phrase should include plural words. The words that are used in the phrase for a
27、voice command should consist of plural syllables. 5.3 Design principle for a voice command 5.3.1 Phonetic description of words Pronunciations of words used in a voice command should be described in an appropriate mark-up way. EXAMPLE International Phonetic Alphabet (IPA), Speech Assessment Methods P
28、honetic Alphabet (SAMPA), etc. NOTE A speech recognition engine does not always distinguish the difference between intonations or accents. 5.3.2 Ease of pronunciation Words used in a voice command should be able to be pronounced easily by a native person, and ideally also by a person with language d
29、ifficulties such as dyslalia, dysphemia, etc. The length of phrase for a voice command should be able to be spoken in one breath. NOTE Combination of words, such as a tongue twister, are difficult to pronounce. 5.3.3 Variation of pronunciation If a word that has more than two pronunciations is used,
30、 all variations of pronunciations shall be registered to the voice command attribute (see ISO/IEC 30122-1).2 ISO/IEC 2017 All rights reserved BS ISO/IEC 30122-2:2017 ISO/IEC 30122-2:2017(E) 5.4 Test of speech recognition engine 5.4.1 General This subclause provides how to test the speech recognition
31、 engine to be used to recognize voice commands. This subclause provides only test and evaluation methods and does not provide quantitative criterions of specification. 5.4.2 Subject At least 10 subjects shall participate in the test. Ideally, not less than 100 subjects should participate. Subjects s
32、hould be selected from diverse demographic groups such as the following: a) age; b) gender; c) native language; d) culture; e) physical condition (person with or without disability); f) geographic location. Subjects can be classified into the following four groups. Subjects from all four groups shou
33、ld be included as participants for the test. a) subjects who are using voice commands frequently; b) subjects who have experience using voice commands; c) subjects who have no experience using voice commands; d) blind and visually impaired people could be associated for a different test for evaluati
34、on. 5.4.3 Samples of a voice command Samples of a voice command to be used for the test should be selected from the following groups: a) voice commands that are frequently used; b) voice commands that are important for system specification; c) voice commands that are estimated to be difficult for a
35、speech recognition engine to recognize; d) voice commands that are chosen randomly. The number of samples of a voice command shall be at least 10. It should be as many as possible. 5.4.4 Conditions of test The speech recognition engine should be tested in realistic conditions of use. EXAMPLE A car n
36、avigation test is conducted in the same signal-to-noise ratio condition of driving. 5.4.5 Procedure of test The subject speaks the sample of a voice command, and the spoken sample is directly provided or is recorded at once and will be later provided to the speech recognition engine. ISO/IEC 2017 Al
37、l rights reserved 3 BS ISO/IEC 30122-2:2017 ISO/IEC 30122-2:2017(E) The test shall be conducted multiple times in different conditions for one sample per one subject. 5.4.6 Results From the recognition results of the tests, the following evaluation indexes can be found. When the evaluation results a
38、re reported, it should include the test conditions such as the number of subjects, the environment, etc. Sentence recognition ratio is determined by Formula (1). (1) Word recognition ratio is determined by Formula (2). (2) Word accuracy is determined by Formula (3). (3) where the “inserted error wor
39、ds” are the recognized words though they were not in the test samples.4 ISO/IEC 2017 All rights reserved BS ISO/IEC 30122-2:2017 ISO/IEC 30122-2:2017(E) Bibliography 1 ISO 5127:2001, Information and documentation Vocabulary 2 ISO 8253-3:2012, Acoustics Audiometric test methods Part 3: Speech audiome
40、try 3 ISO 9241-14, Ergonomic requirements for office work with visual display terminals (VDTs) Part 14: Menu dialogues 4 ISO 9241-15, Ergonomic requirements for office work with visual display terminals (VDTs) Part 15: Command dialogues 5 ISO 9241-110, Ergonomics of human-system interaction Part 110
41、: Dialogue principles 6 ISO 9241-143, Ergonomics of human-system interaction Part 143: Forms 7 ISO 24613, Language resource management Lexical markup framework (LMF) 8 ISO 24614-1, Language resource management Word segmentation of written texts Part 1: Basic concepts and general principles 9 ISO 246
42、15-1:2014, Language resource management Syntactic annotation framework (SynAF) Part 1: Syntactic model 10 ISO/IEC 2382:2015, Information technology Vocabulary 11 ISO/IEC 30122-1, Information technology User interfaces Voice commands Part 1: Framework and general guidance 12 IPSJ-TS 0011:2005, Guidel
43、ines for evaluation of an in-car speech recognition system 13 JEITA IT -4003: 2005, Symbols for Japanese speech recognizer 14 JEITA IT -4005: 2008, The Guidelines for performance evaluation of speech recognition engine 15 JEITA IT -4007: 2012, The Guidelines for Design of Voice Commands in Applicati
44、on Systems with Speech Recognition ISO/IEC 2017 All rights reserved 5 BS ISO/IEC 30122-2:2017This page deliberately left blankThis page deliberately left blankBSI is the national body responsible for preparing British Standards and other standards-related publications, information and services. BSI
45、is incorporated by Royal Charter. British Standards and other standardization products are published by BSI Standards Limited. British Standards Institution (BSI) About us We bring together business, industry, government, consumers, innovators and others to shape their combined experience and expert
46、ise into standards -based solutions. The knowledge embodied in our standards has been carefully assembled in a dependable format and refined through our open consultation process. Organizations of all sizes and across all sectors choose standards to help them achieve their goals. Information on stan
47、dards We can provide you with the knowledge that your organization needs to succeed. Find out more about British Standards by visiting our website at or contacting our Customer Services team or Knowledge Centre. Buying standards You can buy and download PDF versions of BSI publications, including B
48、ritish and adopted European and international standards, through our website at where hard copies can also be purchased. If you need international and foreign standards from other Standards Development Organizations, hard copies can be ordered from our Customer Services team. Copyright in BSI publications All the content in BSI publications, includ
