Ergonomics of human-system interaction - Part 154: Interactive voice response (IVR) applications (ISO 9241-154:2013)

ISO 9241-154:2013 gives guidance on, and requirements for, the user interface design of interactive voice response (IVR) applications. It covers both IVR systems that employ touchtone input and those using automated speech recognition (ASR) as the input mechanism. It is equally applicable to cases in which the caller or the IVR system itself (e.g. in some telemarketing applications) initiates the call. It is intended to be used together with ISO/IEC 13714.

Ergonomie der Mensch-System-Interaktion - Teil 154: Sprachdialogsysteme (ISO 9241-154:2013)

Dieser Teil der ISO 9241 enthält Anleitungen und Empfehlungen zur Gestaltung von Benutzungsschnittstellen von Sprachdialogsystemen. Er behandelt sowohl Sprachdialogsysteme, die das Tonwahlverfahren verwenden als auch die Systeme, die automatische Spracherkennung als Eingabeform verwenden. Er gilt gleichermaßen für Fälle, in denen der Anrufer oder das Sprachdialogsystem selbst (z. B. in einigen Fernsehmarketing-anwendungen) den Anruf initiieren.
Dieser Teil der ISO 9241 soll zusammen mit ISO/IEC 13714 angewendet werden.
ANMERKUNG   Dieser Anwendungsbereich ist daher allgemeiner als der von ISO/IEC 13714, die spezifisch für Sprachmitteilungssysteme gilt.

Ergonomie de l'interaction homme-système - Partie 154: Applications de réponse vocale interactive (RVI) (ISO 9241-154:2013)

L'ISO 9241-154:2013 présente des recommandations et des exigences relatives à la conception de l'interface utilisateur des applications de serveur vocal interactif (SVI). Elle couvre à la fois les systèmes SVI qui utilisent l'entrée de touches et ceux utilisant la reconnaissance automatisée de la parole (RAP) comme un mécanisme d'entrée. Elle est également applicable aux cas où l'appelant ou le système SVI lui-même (par exemple, dans certaines applications de télémarketing) lance l'appel. Elle est destinée à être utilisée conjointement avec l'ISO/CEI 13714.

Ergonomija medsebojnega vpliva človek-sistem - 154. del: Interaktivne aplikacije za glasovni odziv (ISO 9241-154:2013)

Ta del standarda ISO 9241 vsebuje navodila in zahteve za izdelavo uporabniškega vmesnika interaktivnih aplikacij za glasovni odziv (IVR). Zajema interaktivne sisteme za glasovni odziv s tonskim vnašanjem in sisteme, ki za vnos uporabljajo samodejno prepoznavanje govora (ASR). Enako se uporablja za primere, v katerih klic opravi klicatelj ali sam interaktivni sistem za glasovni odziv (npr. v nekaterih telemarketinških aplikacijah). Ta del standarda ISO 9241 je namenjen za uporabo skupaj s standardom ISO/IEC 13714. OPOMBA Področje uporabe tega standarda je tako bolj splošno od področja uporabe standarda ISO/IEC 13714, ki se uporablja posebej za sisteme glasovnega sporočanja.

General Information

Status
Published
Publication Date
12-Feb-2013
Withdrawal Date
30-Aug-2013
Technical Committee
CEN/TC 122 - Ergonomics
Current Stage
6060 - Definitive text made available (DAV) - Publishing
Start Date
13-Feb-2013
Completion Date
13-Feb-2013

Overview

EN ISO 9241-154:2013 - "Ergonomics of human‑system interaction - Part 154: Interactive voice response (IVR) applications" provides guidance and requirements for the user interface design of IVR systems. It covers both touchtone (DTMF) and automated speech recognition (ASR) input mechanisms and applies whether the caller or the system initiates the call. The standard is part of the ISO 9241 ergonomics family and is intended to be used together with ISO/IEC 13714.

Key topics and technical requirements

The standard addresses practical, usability-focused aspects of IVR and speech dialog design, including:

  • Input handling

    • Guidance for touchtone (DTMF) and speech (ASR) input, vocabulary and grammar choices, and enrolment procedures.
    • Managing variable-length input, delimiters (e.g., pound/#), key assignments and minimization of caller key presses.
  • Speech-specific requirements

    • Recommendations on phonetically distinct vocabularies, use of dynamic grammars, turn-taking and end-pointing, and handling time-outs and barge-in behavior.
  • Information output and prompts

    • Construction of prompts and announcements, prompt length and structure, and context-sensitive versus global messages.
  • Navigation and control

    • Features such as skip-forward, dial-through/talk-through, dial-ahead/talk-ahead, global commands and restricted/allowed barge-in.
  • Help and human escalation

    • Context-sensitive and caller-selectable help, prompting for human representative access, transfer initiation and delay handling.
  • Feedback, confirmation and errors

    • Feedback timing, confirmation dialogues, managing unavailable options, informative error messages and handling extended hold situations.
  • Conformance

    • Conformance criteria and relationship to related standards (e.g., ISO/IEC 13714).

Practical applications and who uses this standard

EN ISO 9241-154 is intended for professionals responsible for the design, implementation and evaluation of IVR and speech-dialog systems, including:

  • UX and human‑factors designers focusing on telephony and voice UX
  • IVR platform vendors and telephony system integrators
  • Call centre architects and operations managers
  • ASR/speech recognition developers and speech scientists
  • Accessibility specialists ensuring equitable access to voice systems

Applying this standard improves IVR usability, reduces caller frustration, lowers containment and transfer rates, and increases automation success for both touchtone and speech-enabled services.

Related standards

  • ISO/IEC 13714 (referenced for complementary guidance)
  • Other parts of ISO 9241 (ergonomics of human‑system interaction) for broader usability requirements

Keywords: EN ISO 9241-154, ISO 9241-154:2013, IVR, interactive voice response, ASR, touchtone, speech recognition, voice UX, ergonomics, human-system interaction.

Standard

EN ISO 9241-154:2013

English language
46 pages
Preview
Preview
e-Library read for
1 day

Frequently Asked Questions

EN ISO 9241-154:2013 is a standard published by the European Committee for Standardization (CEN). Its full title is "Ergonomics of human-system interaction - Part 154: Interactive voice response (IVR) applications (ISO 9241-154:2013)". This standard covers: ISO 9241-154:2013 gives guidance on, and requirements for, the user interface design of interactive voice response (IVR) applications. It covers both IVR systems that employ touchtone input and those using automated speech recognition (ASR) as the input mechanism. It is equally applicable to cases in which the caller or the IVR system itself (e.g. in some telemarketing applications) initiates the call. It is intended to be used together with ISO/IEC 13714.

ISO 9241-154:2013 gives guidance on, and requirements for, the user interface design of interactive voice response (IVR) applications. It covers both IVR systems that employ touchtone input and those using automated speech recognition (ASR) as the input mechanism. It is equally applicable to cases in which the caller or the IVR system itself (e.g. in some telemarketing applications) initiates the call. It is intended to be used together with ISO/IEC 13714.

EN ISO 9241-154:2013 is classified under the following ICS (International Classification for Standards) categories: 13.180 - Ergonomics; 35.180 - IT Terminal and other peripheral equipment; 35.240.99 - IT applications in other fields. The ICS classification helps identify the subject area and facilitates finding related standards.

EN ISO 9241-154:2013 is available in PDF format for immediate download after purchase. The document can be added to your cart and obtained through the secure checkout process. Digital delivery ensures instant access to the complete standard document.

Standards Content (Sample)


SLOVENSKI STANDARD
01-april-2013
(UJRQRPLMDPHGVHERMQHJDYSOLYDþORYHNVLVWHPGHO,QWHUDNWLYQHDSOLNDFLMH
]DJODVRYQLRG]LY ,62
Ergonomics of human-system interaction - Part 154: Interactive voice response (IVR)
applications (ISO 9241-154:2013)
Ergonomie der Mensch-System-Interaktion - Teil 154: Dialogführung mittels
Sprachdialogsystemen (ISO 9241-154:2013)
Ergonomie de l'interaction homme-système - Partie 154: Applications de réponse vocale
interactive (RVI) (ISO 9241-154:2013)
Ta slovenski standard je istoveten z: EN ISO 9241-154:2013
ICS:
13.180 Ergonomija Ergonomics
35.240.99 8SRUDEQLãNHUHãLWYH,7QD IT applications in other fields
GUXJLKSRGURþMLK
2003-01.Slovenski inštitut za standardizacijo. Razmnoževanje celote ali delov tega standarda ni dovoljeno.

EUROPEAN STANDARD
EN ISO 9241-154
NORME EUROPÉENNE
EUROPÄISCHE NORM
February 2013
ICS 13.180; 35.180
English Version
Ergonomics of human-system interaction - Part 154: Interactive
voice response (IVR) applications (ISO 9241-154:2013)
Ergonomie de l'interaction homme-système - Partie 154: Ergonomie der Mensch-System-Interaktion - Teil 154:
Applications de réponse vocale interactive (RVI) (ISO 9241- Dialogführung mittels Sprachdialogsystemen (ISO 9241-
154:2013) 154:2013)
This European Standard was approved by CEN on 28 December 2012.

CEN members are bound to comply with the CEN/CENELEC Internal Regulations which stipulate the conditions for giving this European
Standard the status of a national standard without any alteration. Up-to-date lists and bibliographical references concerning such national
standards may be obtained on application to the CEN-CENELEC Management Centre or to any CEN member.

This European Standard exists in three official versions (English, French, German). A version in any other language made by translation
under the responsibility of a CEN member into its own language and notified to the CEN-CENELEC Management Centre has the same
status as the official versions.

CEN members are the national standards bodies of Austria, Belgium, Bulgaria, Croatia, Cyprus, Czech Republic, Denmark, Estonia,
Finland, Former Yugoslav Republic of Macedonia, France, Germany, Greece, Hungary, Iceland, Ireland, Italy, Latvia, Lithuania,
Luxembourg, Malta, Netherlands, Norway, Poland, Portugal, Romania, Slovakia, Slovenia, Spain, Sweden, Switzerland, Turkey and United
Kingdom.
EUROPEAN COMMITTEE FOR STANDARDIZATION
COMITÉ EUROPÉEN DE NORMALISATION

EUROPÄISCHES KOMITEE FÜR NORMUNG

Management Centre: Avenue Marnix 17, B-1000 Brussels
© 2013 CEN All rights of exploitation in any form and by any means reserved Ref. No. EN ISO 9241-154:2013: E
worldwide for CEN national Members.

Contents Page
Foreword .3

Foreword
This document (EN ISO 9241-154:2013) has been prepared by Technical Committee ISO/TC 159
"Ergonomics" in collaboration with Technical Committee CEN/TC 122 “Ergonomics” the secretariat of which is
held by DIN.
This European Standard shall be given the status of a national standard, either by publication of an identical
text or by endorsement, at the latest by August 2013, and conflicting national standards shall be withdrawn at
the latest by August 2013.
Attention is drawn to the possibility that some of the elements of this document may be the subject of patent
rights. CEN [and/or CENELEC] shall not be held responsible for identifying any or all such patent rights.
According to the CEN-CENELEC Internal Regulations, the national standards organizations of the following
countries are bound to implement this European Standard: Austria, Belgium, Bulgaria, Croatia, Cyprus, Czech
Republic, Denmark, Estonia, Finland, Former Yugoslav Republic of Macedonia, France, Germany, Greece,
Hungary, Iceland, Ireland, Italy, Latvia, Lithuania, Luxembourg, Malta, Netherlands, Norway, Poland, Portugal,
Romania, Slovakia, Slovenia, Spain, Sweden, Switzerland, Turkey and the United Kingdom.
Endorsement notice
The text of ISO 9241-154:2013 has been approved by CEN as EN ISO 9241-154:2013 without any
modification.
INTERNATIONAL ISO
STANDARD 9241-154
First edition
2013-02-01
Ergonomics of human-system
interaction —
Part 154:
Interactive voice response (IVR)
applications
Ergonomie de l’interaction homme-système —
Partie 154: Applications de réponse vocale interactive (RVI)
Reference number
ISO 9241-154:2013(E)
©
ISO 2013
ISO 9241-154:2013(E)
© ISO 2013
All rights reserved. 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 ISO at the address below or ISO’s member body in the country of
the requester.
ISO copyright office
Case postale 56 • CH-1211 Geneva 20
Tel. + 41 22 749 01 11
Fax + 41 22 749 09 47
E-mail copyright@iso.org
Web www.iso.org
Published in Switzerland
ii © ISO 2013 – All rights reserved

ISO 9241-154:2013(E)
Contents Page
Foreword .v
Introduction .vii
1 Scope . 1
2 Normative references . 1
3 Terms and definitions . 1
4 Conformance . 7
5 Voice messaging systems . 8
6 Information input . 8
6.1 General . 8
6.2 Informing text telephone users of acceptable input types . 8
6.3 Non-duplication of information input . 8
6.4 Using system information to improve efficiency . 8
6.5 Changing information that has been entered . 9
7 Speech input . 9
7.1 Vocabulary choices for speech-enabled IVRs . 9
7.2 Phonetically distinct vocabulary in speech-enabled IVR applications . 9
7.3 State-specific grammar . 9
7.4 Synonyms in grammars . 9
7.5 Use of dynamic grammars .10
7.6 Enrolment .10
7.7 End-pointing and turn-taking .10
7.8 Handling time-outs for speech input .10
7.9 Speech IVRs with touchtone .11
8 Touchtone input .11
8.1 Indicating touchtone capability .11
8.2 Key assignment for delimiters .11
8.3 Pound (“#”) key in fixed length data entry .11
8.4 Handling time-outs for variable length touchtone input .11
8.5 Key assignments for affirmative and negative responses .11
8.6 Key assignment for the human “help” function .12
8.7 Minimization of caller key presses .12
9 Information output .12
9.1 General provisions for prompts and announcements.12
9.2 Construction of prompts and announcements .15
10 Navigation .19
10.1 Skip-forward function .19
10.2 Dial-through and talk-through .19
10.3 Dial-ahead and talk-ahead .20
10.4 Global commands .20
10.5 Barge-in as a default .20
10.6 Restricting barge-in .20
11 Help .20
11.1 Context-sensitive help .20
11.2 Caller-selectable help .20
11.3 Referencing help in initial prompt .21
11.4 Help commands .21
11.5 System-initiated help .21
12 Access to human representatives .21
12.1 General .21
ISO 9241-154:2013(E)
12.2 Equal access .21
12.3 Prompting access .21
12.4 Initiating transfer .22
12.5 Delays in access .22
12.6 Assistance from human representatives .22
12.7 Human help not available .23
13 Feedback .23
13.1 General .23
13.2 Feedback to caller input .23
13.3 Feedback following selection of unavailable options .23
13.4 System response time .23
13.5 Appropriate context for feedback messages .23
13.6 Landmarks .24
13.7 Confirmation dialogues .24
13.8 Intelligent use of confirmation rejections .25
13.9 Additional feedback in delay situations .26
13.10 Managing extended hold situations .26
13.11 Suggesting that the caller call back .26
14 Errors .26
14.1 General .26
14.2 Unavailability of service .26
14.3 Input prompt repetitions .27
14.4 Error message content .27
14.5 Two consecutive input entry errors in touchtone-based IVRs .27
14.6 Two or more consecutive input entry errors in speech-enabled IVRs .27
14.7 Handling of numerous errors .27
14.8 Avoiding pejorative wording in error messages .27
14.9 Critical messages .28
14.10 Error recovery .28
14.11 Disconnection messages .28
14.12 Exiting due to exceeding error limit .28
14.13 Referencing help .28
14.14 Error prompt wording .28
14.15 Cueing the caller about desired speech input .28
14.16 Conversational repair .28
14.17 Handling too much speech input .29
14.18 Mentioning touchtone options for speech IVRs .29
Annex A (informative) Overview of the ISO 9241 series .30
Annex B (informative) The role of speech recognition errors in IVR design .31
Bibliography .34
iv © ISO 2013 – All rights reserved

ISO 9241-154:2013(E)
Foreword
ISO (the International Organization for Standardization) is a worldwide federation of national standards
bodies (ISO member bodies). The work of preparing International Standards is normally carried out
through ISO technical committees. Each member body interested in a subject for which a technical
committee has been established has the right to be represented on that committee. International
organizations, governmental and non-governmental, in liaison with ISO, also take part in the work.
ISO collaborates closely with the International Electrotechnical Commission (IEC) on all matters of
electrotechnical standardization.
International Standards are drafted in accordance with the rules given in the ISO/IEC Directives, Part 2.
The main task of technical committees is to prepare International Standards. Draft International
Standards adopted by the technical committees are circulated to the member bodies for voting.
Publication as an International Standard requires approval by at least 75 % of the member bodies
casting a vote.
Attention is drawn to the possibility 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.
ISO 9241-154 was prepared by Technical Committee ISO/TC 159, Ergonomics, Subcommittee SC 4,
Ergonomics of human–system interaction.
ISO/TS 9241 consists of the following parts, under the general title Ergonomic requirements for office
work with visual display terminals (VDTs):
— Part 1: General introduction
— Part 2: Guidance on task requirements
— Part 5: Workstation layout and postural requirements
— Part 6: Guidance on the work environment
— Part 11: Guidance on usability
— Part 12: Presentation of information
— Part 13: User guidance
— Part 14: Menu dialogues
— Part 15: Command dialogues
— Part 16: Direct manipulation dialogues
ISO 9241 also consists of the following parts, under the general title Ergonomics of human-system interaction:
— Part 20: Accessibility guidelines for information/communication technology (ICT) equipment and services
— Part 100: Introduction to standards related to software ergonomics [Technical Report]
— Part 110: Dialogue principles
— Part 129: Guidance on software individualization
— Part 143: Forms
— Part 151: Guidance on World Wide Web user interfaces
— Part 154: Interactive voice response (IVR) applications
— Part 171: Guidance on software accessibility
ISO 9241-154:2013(E)
— Part 210: Human-centred design for interactive systems
— Part 300: Introduction to electronic visual display requirements
— Part 302: Terminology for electronic visual displays
— Part 303: Requirements for electronic visual displays
— Part 304: User performance test methods for electronic visual displays
— Part 305: Optical laboratory test methods for electronic visual displays
— Part 306: Field assessment methods for electronic visual displays
— Part 307: Analysis and compliance test methods for electronic visual displays
— Part 308: Surface-conduction electron-emitter displays (SED) [Technical Report]
— Part 309: Organic light-emitting diode (OLED) displays [Technical Report]
— Part 310: Visibility, aesthetics and ergonomics of pixel defects [Technical Report]
— Part 331: Optical characteristics of autosterescopic displays [Technical Report]
— Part 391: Requirements, analysis and compliance test methods for the reduction of photosensitive seizures
— Part 400: Principles and requirements for physical input devices
— Part 410: Design criteria for physical input devices
— Part 411: Evaluation methods for the design of physical input devices [Technical Specification]
— Part 420: Selection of physical input devices
— Part 910: Framework for tactile and haptic interaction
— Part 920: Guidance on tactile and haptic interactions
The following parts are under preparation:
— Part 940: Evaluation of tactile and haptic interactions
User-interface elements, ergonomic requirements for the reduction of visual fatigue from stereoscopic
images, and framework and guidance for gesture interactions are to form the subjects of future parts
161, 392 and 960.
vi © ISO 2013 – All rights reserved

ISO 9241-154:2013(E)
Introduction
This part of ISO 9241 contains provisions specific to interactive voice response (IVR) systems, which
may involve a combination of voice technologies, but are distinguished by the use of the telephone as the
information transfer mechanism. These provisions assume no visual displays of information to the user
beyond the labels on the telephone’s keypad, with the notable exception of text telephones (TTYs), which
have a visual feedback display.
Although it is extremely important that IVR user interface designers take into account the cultural
and linguistic aspects of the user interface that impact the intended user population, these aspects are
beyond the scope of this part of ISO 9241 and are not addressed in this part of ISO 9241 . Similarly, because
automatic speech recognition (ASR) performs differently for different languages and the technology
continues to improve, it is beyond the scope of this document to provide detailed provisions on ASR user
interface design generally. Rather, this part of ISO 9241 focuses on the design of IVR dialogues and
discusses only those ASR user interface design issues that impact dialogue design.
Many current IVR systems pose significant accessibility challenges to callers with disabilities. Some of
the provisions in this part of ISO 9241 were developed specifically to accommodate callers with special
needs, particularly those who are deaf or who have hearing impairments.
The provisions in this document are intended to be compatible with ISO/IEC 13714.
Interactive voice response (IVR) systems became a common means of delivering customer service
in the late 1980s. These systems are designed to reduce or eliminate the need for human-in-the-loop
customer support by automating many of the functions that human customer service representatives
typically provide over the telephone with respect to processing of customer transactions. Thus, users
(i.e. callers) can now engage in such activities as checking train schedules, ordering a book or reporting
problems with their television cable service by interacting with an IVR system. In addition, IVRs often
automate call-routing functions so that the caller can be connected with the right assistance to handle
their specific request.
This part of ISO 9241 is concerned with the design of the human–IVR system dialogue and related topics.
As shown in Figure 1, callers typically interact with the IVR system through one of two methods: speech
or touchtone (DTMF) input via the telephone keypad. If an IVR system is speech-enabled, it employs
an ASR engine that recognizes the speech input from the caller. If it is not speech-enabled, it typically
recognizes only touchtone input from the telephone keypad or, sometimes, TTY input. Speech-enabled
IVR systems are a relatively recent development and many systems are now designed to accept both
touchtone and speech within a given dialogue with a caller. The IVR system responds via hardware
and/or software that presents synthesized, digitized or recorded speech to the caller and that may also
present non-speech audio. The fact that there is no assumed visual display of information to the caller
in these applications poses a challenge to dialogue designers because of the burden placed on the caller
to navigate the application and process and remember the relevant information without the aid of any
visual display.
ISO 9241-154:2013(E)
Figure 1 — IVR system representation
This part of ISO 9241 provides provisions for the design of IVR dialogues in speech-enabled and touchtone-
based IVR systems. Therefore, its focus is on the interface between the caller and IVR software and
application databases, which is mediated by the hardware and software that recognize speech and/or
touchtones, and which present speech output to the caller. Both ASR systems and DTMF recognizers place
constraints on the design of IVR dialogues and those constraints have been considered in developing the
provisions of this part of ISO 9241. However, this document is not intended to address the design of ASR
or DTMF user interfaces generally, for two reasons: first, the technology, particularly for ASR systems,
is still evolving, and second, many ASR user interfaces are designed to include a visual display (e.g.
ASR dictation applications), which IVR applications are not assumed to have.
Lastly, most of the provisions for speech-enabled dialogues are intended for use with grammar-based
IVRs. Although some of the same principles apply to natural language systems (i.e. applications that
use statistical language models), detailed design provisions are not included for these applications in
this part of ISO 9241 because natural language understanding is implemented via a distinct technology
and the use of natural language in speech-enabled IVRs is still evolving. There are also some aspects of
applications design that are different for natural language dialogues, relative to grammar-based ones, in
addition to the differences in dialogue design that relate to speech recognizers specifically.
viii © ISO 2013 – All rights reserved

INTERNATIONAL STANDARD ISO 9241-154:2013(E)
Ergonomics of human-system interaction —
Part 154:
Interactive voice response (IVR) applications
1 Scope
This part of ISO 9241 gives guidance on, and requirements for, the user interface design of interactive
voice response (IVR) applications. It covers both IVR systems that employ touchtone input and those
using automated speech recognition (ASR) as the input mechanism. It is equally applicable to cases in
which the caller or the IVR system itself (e.g. in some telemarketing applications) initiates the call.
This part of ISO 9241 is intended to be used together with ISO/IEC 13714.
NOTE Its scope is thus more general than that of ISO/IEC 13714, which is specific to voice messaging systems.
2 Normative references
The following referenced documents are indispensable for the application of this document. For dated
references, only the edition cited applies. For undated references, the latest edition of the referenced
document (including any amendments) applies.
ISO/IEC 13714, Information technology — Document processing and related communication — User
interface to telephone-based services — Voice messaging applications
ITU-T E 161, Arrangement of digits, letters and symbols on telephones and other devices that can be used for
gaining access to a telephone network
3 Terms and definitions
For the purposes of this document, the following terms and definitions apply.
3.1
announcement
message presented by the IVR to the caller, which informs but does not instruct the caller to act
Note 1 to entry: Some industry standards do not distinguish between announcements and prompts and consider
all system-originated messages to be prompts.
Note 2 to entry: Prompts specifically instruct the caller except for subsequent input from the caller (see 3.33).
3.2
automatic speech recognition
automated speech recognition
ASR
conversion of spoken words to machine-readable input
3.3
barge-in
capability of an IVR system to accept input while a prompt (or an announcement) is being played
Note 1 to entry: The playback of speech ceases immediately and the system responds to the input of the caller.
ISO 9241-154:2013(E)
Note 2 to entry: See dial-through (3.13) and talk-through (3.43). The term “barge-in” is synonymous with the term
“dial-through” for systems employing touchtone input. It is also synonymous with “talk-through” for systems
accepting speech input.
3.4
caller
user who calls for or is called by a service, gets connected to the IVR system, and interacts with it
Note 1 to entry: In an IVR system the caller is considered to be synonymous with the user.
3.5
coaching
instructions to the speakers of the prompts and announcements (also known as the voice talent) about
desired subtleties in the prompt recordings
3.6
concatenated prompts
prompts or announcements constructed by stringing together several individual prompts or
announcements
Note 1 to entry: Concatenated prompts are usually employed for the presentation of information that is dynamic
or context-specific.
3.7
confidence level
commitment with which the speech recognition system returns a recognition result for a given input
Note 1 to entry: See confidence score (3.8).
Note 2 to entry: Confidence levels are often defined by ranges of confidence scores, which are usually classified
as High, Medium and Low. Ranges are then used to trigger certain IVR responses, including acceptance, rejection
or confirmation of caller speech.
3.8
confidence score
score assigned by the ASR system indicating its degree of confidence that it correctly recognized the
caller’s utterance
Note 1 to entry: For every caller input, the ASR system returns a list of potential candidate words or phrases with
a numeric score representing the hypothesized probability of correctness.
3.9
continuous speech recognition
speech recognition that allows continuous input of words or phrases
Note 1 to entry: No minimum duration of silence is required at the beginning or end of words or phrases (other
than the pauses generally occurring in natural speech patterns). Contrast with “Discrete speech recognition”.
3.10
conversational repair
capability of an IVR system to resolve a conversational breakdown that occurs due to a speech or
touchtone input error, by making use of subsequent input by the caller to determine the appropriate
next step in the dialogue
EXAMPLE The caller in a travel arrangements application, when asked his destination, says “Buffalo”. The
IVR system replies, “You want to go to Chicago, correct?” In response, the caller says, “No, Buffalo.” If the system
employs conversational repair, it would be able to determine that the caller has provided “corrective” input and
would attempt to recognize that input and use it to move the dialogue along. Its response might then be. “Oh, you
meant Buffalo. I’m sorry. When would you like to depart?” rather than asking the caller the same initial question
again (i.e. “Where do you want to go?”).
2 © ISO 2013 – All rights reserved

ISO 9241-154:2013(E)
3.11
deletion error
instance of a recognition error where part of a speaker’s utterance is incorrectly omitted in the speech
recognizer’s output
3.12
dial-ahead
capability of an IVR system to accept touchtone input before the system has requested it
Note 1 to entry: The touchtone input is then used by the system based on the order in which the input was received.
This allows callers to provide input without having to listen to the associated input prompts.
Note 2 to entry: See talk-ahead (3.42).
3.13
dial-through
capability in a touchtone-based IVR system to accept caller input while a prompt (or an announcement)
is being played
Note 1 to entry: See talk-through (3.43) and barge-in (3.3).
Note 2 to entry: In response to dial-through, the playback of speech ceases and the system responds to the key
that was pressed.
3.14
digitized speech
digital recording of human speech
Note 1 to entry: Contrast with synthesized speech (3.40), recorded speech (3.35) and text-to-speech (3.45).
3.15
discourse marker
word, phrase or sound that is used as an indication to the caller that a new prompt or announcement is
starting or that the caller is now expected to provide input
Note 1 to entry: Common discourse markers are “okay,” “alright,” and “now.”
3.16
discrete speech recognition
speech recognition that requires a silence of some minimum duration at the beginning and at the end of
the word or phrase to be recognized, to allow proper parsing of speech input
Note 1 to entry: Contrast with continuous speech recognition (3.9).
3.17
dual tone multiple frequency
DTMF
touchtones of the contemporary telephone keypad
3.18
dynamic grammar
grammar which is not predetermined and that is used for speech recognition
EXAMPLE A caller is asked to speak a prescription number for refill and the grammar is composed of only
that caller’s prescription numbers, not all possible numeric combinations.
Note 1 to entry: It is usually created in real-time based on variable data.
ISO 9241-154:2013(E)
3.19
end-pointing
process intended to detect the beginning and end of speech input
Note 1 to entry: In IVR the beginning of speech is typically referred to as onset and the ending of speech is typically
referred to as offset.
3.20
enrolment
procedure by which callers provide training input for speaker-dependent speech recognition systems
that require training before they can be used
3.21
explicit confirmation
method whereby the caller is prompted to confirm his or her input to an IVR system
Note 1 to entry: Contrast with implicit confirmation.
3.22
grammar
body of syntactic, and sometimes morphologic, rules defining all caller utterances that are covered by
the speech recognition system
Note 1 to entry: The grammar specifies the input that is recognized by the application.
3.23
implicit confirmation
method of confirming the caller’s input to an IVR system in which the IVR system responds to that input
as if the input was correct
EXAMPLE 1 If a caller inputs “balance” to indicate that she wants the system to give her the balance in her
bank account, the IVR’s response of “Your balance is $452.19” implicitly indicates that it correctly recognized the
request for “balance” information, as opposed to some other information about the account.
EXAMPLE 2 “Tomorrow.” – IVR system: “At what time do you want to leave tomorrow?”
Note 1 to entry: In the case of implicit confirmation, the caller knows what input was received based on the
subsequent action of the IVR system
Note 2 to entry: Implicit confirmations are a natural way of speeding up the dialogue. However, in the case of an
error (disconfirmation), the mechanism of dialogue repair is not clear.
3.24
insertion error
instance of a recognition error where one or more words in the speech recognizer’s output do not
correspond with any word (or sequence of words) in the speaker’s utterance
3.25
interactive voice response
IVR
software application that a caller interacts with over a telephone line and which presents pre-recorded
and/or dynamically generated speech output and which can accept touchtone and/or speech input
from the caller
3.26
landmark
short phrase or a sound that acts as a heading or launch point for a portion of an IVR dialogue and
which can be used to facilitate navigation of the caller within an IVR application
EXAMPLE Short phrase: “Account Information”, “Repair Services”.
4 © ISO 2013 – All rights reserved

ISO 9241-154:2013(E)
3.27
message
information in an IVR system that is provided by the system, other callers, other subscribers, or
system administrators to the caller
Note 1 to entry: Messages include both prompts (i.e. instructions for action) and announcements (i.e. no
action required).
3.28
mixed initiative
IVR flow that contains both caller and system initiative situations
3.29
natural language understanding
NLU
technology used to recognize certain words and phrases from a caller utterance spoken as if talking
with another human
Note 1 to entry: NLU does not actually understand the caller, but it is used with other technologies to derive the
caller’s meaning.
3.30
open-ended dialogue
dialogue that does not constrain the verbal responses from a caller
EXAMPLE “What can I do for you?”
Note 1 to entry: This is typically used in conjunction with NLU.
3.31
persona
set of personal, human characteristics conveyed by the application through the speakers of
prompts and announcements (sometimes called the voice talent), word choices for prompts and other
stylistic/aesthetic qualities of the IVR
Note 1 to entry: An IVR application persona differs from persona as used in other areas of human–computer
interface design. An IVR application persona gives the caller an impression of the company or organization that
is the focus of the application (e.g. a bank services centre, a retail company), as represented by the voice that
conveys the prompts and announcements within the application. In other areas of human-computer interface
design, a persona is a detailed description of a representative user that is used to guide application design.
3.32
priming
inclusion of example phrases or other prompt techniques to influence the caller’s utterance style and
length in speech-enabled IVR systems
EXAMPLE 1 An IVR banking application prompts caller word choices for menu items by using the specific
words it wants the caller to say in its prompt: “You can pay bills, check your account balance, or make a deposit.”
EXAMPLE 2 “Tell us what you would like to do. You can say ‘pay bills’, ‘check account balance’ or ‘make a
deposit.” Here, the a
...

Questions, Comments and Discussion

Ask us and Technical Secretary will try to provide an answer. You can facilitate discussion about the standard in here.

Loading comments...