Microsoft Speech Server Charlene Volker Solutions Sales

Microsoft Speech Server Charlene Volker – Solutions Sales Specialist Lynn Olson – Technical Specialist

Government Self-Service Applications ¢ ¢ ¢ ¢ Permits and Inspections Jury Management Citation Management Elections Tax Information Utilities Password Reset ¢ ¢ ¢ ¢ Auto Attendant Outbound Notification License Application License Renewal Motor Vehicle Renewal Mobil Workforce Speech Enabled Portals 2

State and Local Governments are looking for IT Solutions That… ¢ Provide a solution for increased services demands by constituents Demonstrate a rapid return on investment Are easy to install and maintain ¢ Address key operational challenges ¢ ¢ Microsoft Speech Technologies provide an easy, economical way to extend government services to a broader range of constituents, across a wide array of devices. 3

Benefits of Speech Recognition ¢ Reduces Labor Costs in the Enterprise n n ¢ Call Center, IT and Operations Automates repetitive high volume, low value tasks Improves Automation n n ¢ Simplifies complex transactions Adds convenient access to existing systems Improves the User Experience n n Speech provides advantages over other methods including touch-tone, email and web 80% believe speech is as easy or better to use than internet 4

Where Speech Fits Customers Reached Web User Friendliness Speech Touch-Tone Accessibility 5

6

7

8

NY DOE Chose Speech Server ¢ New York Department of Education n 1. 2 million students, 80, 000 teachers and 1, 200 schools n Highly Acclaimed Website n Low computer literacy and lack of internet access – Digital Divide n Speech-enabled ASP. NET website n Extends NYDOE website to phone n Provides attendance, grades, lunch menu and other key information to parents “We have a large number of parents who are not comfortable with a computer. But telephones are accessible and easy to use…using Microsoft Speech Technologies, parents will have access to information 24/7. ” Richard Langford, Deputy CIO NYC DOE 9

10

11

Microsoft Speech Technology Vision Making Speech Mainstream Contact Center IVR Messaging Enterprise & LOB Applications Desktop & Embedded Microsoft Developer tools for speech Microsoft Speech Server Speech Technologies “Speech and natural language understanding are the key technologies that will have the most impact in the next 15 years. ” -- Bill Gates 12

Permits and Inspections ¢ ¢ ¢ Schedule Inspections Cancel/Reschedule Inspections Post Inspection Results Obtain Inspection Results Fax Results Outbound Notification 13

Municipal Court Systems ¢ ¢ Check the status of case or citation Check the status of an account n n n ¢ Schedule and/or Confirm n n n ¢ ¢ ¢ Amount Owed Due Date Payment History Court Date Administrative Review Hearing Credit card payment processing Jury Notification Outbound Court Appearance reminder call 14

Tax Assessment & Collections ¢ Status Checks n n n ¢ Prior Year Tax Payments n n ¢ ¢ Current year tax payments 1 st half 2 nd half By year Delinquent or lien status Credit Card Payments of Taxes Fax Options n n Parcel Detail Property and Ownership detail Payment History Billing History 15

Utility Department ¢ Account Inquiry n n n n Current balance Adjusted balance Last payment amount Pending payment Current billing date Delinquent due date Last payment date Delinquent balance ¢ ¢ ¢ Start/Stop Service Payment Site Locator Outbound Notification Meter Reading Outage Reporting and Status 16

Back End Integration ¢ ¢ ¢ ¢ ¢ Microsoft CRM Accela Advantage (Tidemark) Accela Automation Accela Permits Plus Black Bear Computronix CRW CSDC Amanda Echelon 3 Technologies ¢ Eden Hansen Harris Computer Systems KIVA Municipal City. View Pentamation Springbrook Software ¢ Sun. Gard HTE ¢ ¢ ¢ 17

Microsoft’s Auto Attendant ¢ ¢ ¢ Automated operator 55, 000+ names in Microsoft directory Results n n n 75% first-try task completion rate 50% reduction in agent headcount ROI (over 4 years) = 1400% Payback period = 4 months Annual savings = $270, 000 18

What Is Microsoft Speech Server?

R 2 ¢ Web-based, speech-enabled IVR & multimodal server n ¢ ¢ Supports open and industry standards Integrated ASR/TTS n ¢ ¢ ¢ DTMF and speech U. S. English, U. S. Spanish, Canadian French High performance, scalable, reliable, secure Flexible deployment options Comprehensive and robust development using VS. NET and Speech Application SDK Reporting, analysis, and tuning tools Integrated Windows management Leverages existing IT, Web, telephony, and data assets and skills 20

More Self-Service, Less Cost Graphical User Interface Voice User Interface ¢ Application Logic and Business Rules ¢ ¢ Back-end Data ¢ Same development tools Same web and web services infrastructure Same application logic and backend data Same management and monitoring tools 21

Speech Server Topology Microsoft Speech Server PBX Telephony Card TDM Telephony M TD PSTN Media Gatewa y TDM SIP/ R TP SIP/RTP Telephony Interface Manager (TIM) Development Workstation Microsoft® Speech Application SDK + Visual Studio®. NET Ap p. D loy ed HTML + SALT + JScript Web Pages Grammars C, DB , O ces, ET i O. N erv AD eb S AP W SO JH DB Telephony Application Services (TAS) ASP. NET Web Server ep Back-end/DB Connectivity SQL – Logging & Reporting Speech Engine Services (SES) Prompts ASP. NET Controls 22

MSS Configuration Options Standard Edition 24 ports or less Enterprise Edition AIO or Distributed or +1 Microsoft Speech Server (SES service enabled) Load balancer Web Server and DB(s) SOAP Microsoft Speech Server and Web Server or Microsoft Speech Server (TAS service enabled) PBX (optional) PBX o o All-in-one - manageability Distributed - fail-over Universal Port: ASR, TTS, and Languages Licensed per Proc 23

Advantages of Speech ¢ Improve Constituent Satisfaction ¢ Extend Services Easily ¢ Leverage Existing Technology 24

For More Information… ¢ My contact Information n cvolker@microsoft. com ¢ http: //www. microsoft. com/speech/solutions /government/default. mspx ¢ Case Studies n n Data Sheet Sample Application Wav Files 25

© 2003 -2004 Microsoft Corporation. All rights reserved. This presentation is for informational purposes only. Microsoft makes no warranties, express or implied, in this summary. 26

Speech Application SDK Overview ¢ VS. NET integrated tools n n n ¢ ¢ ¢ ASP. NET speech controls Grammar libraries Debugging tools n n n ¢ Debugger Telephony simulator Log player Analysis tools n n ¢ Dialog Grammar Prompts Call analyzer Reports Samples, tutorials, docs 27

Building a Speech Application ¢ ¢ ¢ Design the VUI interaction – Call Flow Create grammars for expected answers Add speech controls to a Web Form Extract the meaning (answers) of the recognition results and bind them to controls Create the prompts Debug before deploying Grammar Editor Dialog Editor Prompt Editor Debugging Tools 28

Grammars 29

What are Grammars? ¢ ¢ A structured list of rules that identify the words or phrases that can be used for speech input and subsequent automatic recognition Maintained in. grxml files – adhere to the SRGS format Semantic Items Preamble I would like a I’ll have a a Give me a small medium large Postamble plain pizza cheese pizza please mushroom ham 30

Grammar Elements ¢ ¢ ¢ Phrase (words) List (alternatives) Rule reference Group (rolls Lists up) Advanced: n n n ¢ Wildcard Halt Skip Script Tag (assigns variable) 31

Creating Grammars and Semantic Mark-up 32

Adding Semantic Mark-up ¢ ¢ Add Script Tags to your grammar rules n After the phrase where a semantic value is required n This creates elements in the underlying. grxml file Use the Semantic Script Editor to create script n Create semantic elements and attributes n Use free format script editing for complex requirements 33

Speech Controls 34

Speech Controls Basic Speech Controls Dialog Speech Controls Application Speech Controls Listen QA Credit. Card. Number Prompt Semantic. Map Phone Semantic. Item Data. Table. Navigator Compare. Validator / Custom. Validator Custom Controls Answer. Call Grammar Command 35

What are Application Speech Controls? ¢ Composite controls, to collect common information Dialog Speech Controls Grammars Application Control Default Prompts ¢ Examples include date, phone number and credit card controls 36

What are QA Controls? ¢ A QA manages a questionanswer interaction with a user n n Asks a question (prompts the user) Accepts voice input (using a grammar) Question. Answer Interactions Application qa. PSize qa. PTopping Which size Pizza would you like to have? What toppings would you like on your pizza? 37

Semantic Items and Semantic Map ¢ ¢ Semantic items store elements of contextual information gathered from the user A semantic map is a container for multiple semantic items QA Control(s) Answers Collection Semantic. Map si. PSize si. PTopping Semantic Item State Empty Needs Confirmation Confirmed 38

Dialog Control Editor 39

Prompts 40

MSS Prompts ¢ ¢ Supports Pre-Recorded and Text-to. Speech Stored in a Prompt Database n ¢ Easy to Manage Prompt DB and Editor enable you to: n n n Add Transcriptions Create Extractions Record Prompts Edit Wave Files Validate Prompt Coverage 41

The Prompt Editor 42

Speech Debugging 43

The Telephony Application Simulator 44

The Speech Debugging Console Break on Listen Start Play Prompts Enable SML Editing Text or Voice Input Simulated Exception Conditions Edit SML Results Speech Control State Trace Output 45

Managing your MSS Deployment ¢ Microsoft Management Console (MMC) n n n ¢ Windows Management Instrumentation (WMI) n n n ¢ SES, TAS, TIM Application deployment Centralized settings and replication All settings can be configured programmatically Uniform access for mgmt data from multiple sources Sharing mgmt data across multiple mgmt applications App Provisioning Tool 46

Monitoring your MSS Deployment ¢ Real-time monitoring facilities n n ¢ ¢ Centralized Monitoring via MMC SNMP n ¢ ¢ System monitor (disk, memory, proc, net, etc) Performance monitor (counters, traces, alerts) Events can be configured to generate traps MOM Management Pack Log Analysis Tools 47

Data Analysis Framework Application 48

Reporting and Tuning ¢ Scenarios n Business Manager n Application Developer n how good are my grammars? where are people hanging up/transferring? System administrator ¢ how many calls? which services? how many successful transactions? where are the system latencies? what is causing trace warning messages? MSS solutions n n Speech Application Reports Call Viewer 49

Call Viewer ¢ Analyst selects problematic calls n queries over times, events, particular properties ¢ quickly retrieves all calls symptomatic of the problem Drills down into the call n flexible views, according to event filters selected turn by turn w component event by component event w including user audio detailed information even finer-grained configuration w conditional event filtering 50

Call Viewer 51

Reports Call Aggregates Provides total calls aggregated by various time periods Call Volume Displays call volume across a single span of time, plus providing comparative data on disconnection types, transferred calls, and call duration. Dialog Overview For the selected time period, displays data on QA use and QA recognition confidence scores, plus command use. Errors Displays summary data on call completion, a count of tasks missing Task. Start and Task. Complete events, and occurrence counts for error event types. Messages Provides counts of messages sent by the SALT Log. Message function, and a breakdown by message name and content. Prompts Provides counts for bargein and user-perceived latencies, prompt ending status, individual prompt totals, and comparison of text-tospeech versus recorded prompts. Server Statistics Provides data on latencies, channel and port usage, and answering time. Turn Analysis Displays data on QA usage per call, sums and percentages for QA History values, compares speech versus DTMF input, and reports on time spent on pages. Tasks Reports on task completion, duration and progress, and the count of QAs used for each task. 52

© 2003 -2004 Microsoft Corporation. All rights reserved. This presentation is for informational purposes only. Microsoft makes no warranties, express or implied, in this summary. 53