What makes a successful speech-enabled call routing application? - - PowerPoint PPT Presentation

▶
what makes a successful speech enabled call routing
SMART_READER_LITE
LIVE PREVIEW

What makes a successful speech-enabled call routing application? - - PowerPoint PPT Presentation

Aug 25, 2022 101 likes •272 views

What makes a successful speech-enabled call routing application? Diana Binnenpoorte and Dorota Iskra LangTech February 28 - 29, 2008 Rome, Italy 1 Overview Who are we? Why speech-enabled call routing? What is speech-enabled

slide-1
SLIDE 1

1

LangTech February 28 - 29, 2008 – Rome, Italy

What makes a successful speech-enabled call routing application?

Diana Binnenpoorte and Dorota Iskra

slide-2
SLIDE 2

2

LangTech February 28 - 29, 2008 – Rome, Italy

  • Who are we?
  • Why speech-enabled call routing?
  • What is speech-enabled call routing?
  • Performance measures
  • Success factors in various phases
  • Summary

Overview

slide-3
SLIDE 3

3

LangTech February 28 - 29, 2008 – Rome, Italy

Who are we?

LogicaCMG and speech technology:

  • The VOICE team as part of Customer Contact Solutions
  • Expertise on the design, implementation and integration of

telephony self services in existing architectures

slide-4
SLIDE 4

4

LangTech February 28 - 29, 2008 – Rome, Italy

Examples of applications

  • CLAIRE: a 24 hour speech-driven operator and receptionist
  • Mobile ticket service: mixed-initiative dialogue system through

which mobile phone users can specify their journey and order tickets

  • Stock Information Speech Portal: open dialogue system in

which users can request share holder’s information, information

  • n funds, tips and so on. The system takes into account the

expertise of the user

  • Call routing applications
  • Voice Verification: users get access to their accounts based
  • n biometric data of their voice (not yet fully implemented)
slide-5
SLIDE 5

5

LangTech February 28 - 29, 2008 – Rome, Italy

Why speech-enabled call routing? (1)

  • Route calling customers to appropriate agent or service in call

center

  • Customers usually press keys: touch-tone IVR
  • Touch-tone IVR menus remote from customer’s intuition:

– Many time-outs – Wrong choices – Transfers to operator – Pressing ‘0’

  • IVR menus needed in large organizations:

– One contact number – Specialized agents

slide-6
SLIDE 6

6

LangTech February 28 - 29, 2008 – Rome, Italy

Why speech-enabled call routing? (2)

Speech-enabled call routing:

  • Facilitates same functionality as touch-tone IVR
  • Open Speech Recognition
  • Much more customer-friendly:

– Customer is free to speak question in a natural way – Customer no longer needs to choose – Shorter and more efficient dialogues

slide-7
SLIDE 7

7

LangTech February 28 - 29, 2008 – Rome, Italy

What is speech-enabled call routing?

  • pen

speech recognition classifi- cation filtering n-best list candi- dates agent of service un- decided dialogue manager

slide-8
SLIDE 8

8

LangTech February 28 - 29, 2008 – Rome, Italy

Performance measures

  • Success of spoken dialogue systems often expressed in:

– Dialogue Success Rate – Recognition accuracy: Word Error Rate

  • BUT, is the application:

– widely used? – appreciated by customers? – appreciated by employees of service provider?

  • THEREFORE, other factors:

– Customer experience – Involvement within organization

slide-9
SLIDE 9

9

LangTech February 28 - 29, 2008 – Rome, Italy

Various phases of system development

Design phase:

  • Establishing functionalities
  • Dialogue design
  • Determining exit points

Building phase:

  • Coding and testing
  • Collecting training material

Deployment phase:

  • Training call center agents
  • Business intelligence
slide-10
SLIDE 10

10

LangTech February 28 - 29, 2008 – Rome, Italy

Design phase (1)

(Q1.0) “Open vraag: waar belt u over” OPEN (page 1)

1-9-2006 Page 1 Open

Speech Navigation

Prompt (pNR) “Niet gehoord” Prompt (pNU) “Niet verstaan” REPEAT OPEN (page 2) NOT_RECORDED TOO_LONG =2 OR 3 EXIT2-3 (page 4) EXIT1 (page 5) NOT_UNDERSTOOD Prompt (pBreak, pBreak2) <beep> “Sorry, onderbreken” Irritation_Q+1 =0 OR > 3 NO Round = from Open to Open, excluding DTMF parts Irritation_Q = round dependent irritation factor Level 0 and level 1 Identification (from 'Voorportaal') filtering (M4) YES Reset round dependent parameter (M3) Session data Prompt (pUitleg) “Dit systeem ...” =< frequency threshold FLEXIBLE DIALOGUE BLOCK (page 7) NO YES Prompt (pActionLabel) “Actie label” YES NO ActionLabel parameter Collect session data (M1) Prompt (pNU23) “Niet helemaal verstaan” Set round + 1 (M2) Set location code (M5) =1 Flexible dialogue parameter irritation threshold exceeded? NO Execute (page 6) YES 2nd ROUND FROM EXECUTE (page 6) Session data Access table call frequency_novice parameter > frequency threshold NO Prompt (pUitlegDemo) “Dit is een demo ...” YES (Q1.0a) “Open vraag: waar belt u nog meer over, anders hang op” D8 ROUND = 1? D1 ACTION LABEL_1? D2 Call frequency_no vice? D4 FLEXIBLE DIALOGUE BLOCK_1? D3 INPUT? D6 # of EXITS? D7 DEMO_1? D5

Dialogue design

  • Contradicting interests:

– Technical performance – Customer experience – Organizational issues

  • Influences all performance measures
slide-11
SLIDE 11

11

LangTech February 28 - 29, 2008 – Rome, Italy

Design phase (2)

Determining exit points

  • Agents are skilled in different tasks, answering various types of

questions, i.e. categories

  • Organization of call center leading in selecting exit points?
  • Customer centered approach
  • Number of exit points
  • Influences all performance measures
slide-12
SLIDE 12

12

LangTech February 28 - 29, 2008 – Rome, Italy

Building phase (1)

Collecting training material, i.e. collection of tagged sentences

  • “The more the better”?
  • Well-distributed over exit-points
  • Training material should resemble real customer questions:

– Terminology and formulation – Variance

slide-13
SLIDE 13

13

LangTech February 28 - 29, 2008 – Rome, Italy

Building phase (2)

  • Collecting strategies:

– Spoken material (live or simulated) – Written material (natural or simulated)

  • Influences technical measures and involvement within
  • rganization
slide-14
SLIDE 14

14

LangTech February 28 - 29, 2008 – Rome, Italy

Deployment phase

Training call center agents

  • Learn new conversational techniques
  • Learn how to interpret recognized sentence

Business intelligence

  • Valuable information can be retrieved, e.g.

– Statistics, e.g. load effect on call center – Effect of marketing campaign

  • Both increase the support within organization
slide-15
SLIDE 15

15

LangTech February 28 - 29, 2008 – Rome, Italy

Summary

  • Besides commonly used technical performance measures

also other factors play important role in the success of a speech-enabled call routing application

  • These factors are customer experience and involvement

within organization

  • During various phases of implementation these factors play an

important role

  • Sometimes conflicting interests
slide-16
SLIDE 16

16

LangTech February 28 - 29, 2008 – Rome, Italy

Thank you! Questions?