EDUCATION


Business Intelligence From Mining
     VoIP Voice Recordings
           Ray Lucchesi, Silverton Consulting, In...
SNIA Legal Notice
                                                                     EDUCATION



• The material contain...
Abstract                                                            EDUCATION



Business Intelligence From Mining VoIP Vo...
VoIP recording agenda
                                                                     EDUCATION




• Voice recording...
VoIP architecture
                                                                                     EDUCATION




     ...
VoIP adoption
                                                                     EDUCATION



• Predicting >50% of enter...
Why companies record
voice                                                                EDUCATION




• Quality assuranc...
Legal Concerns
                                                                     EDUCATION




• USA allows recording c...
VoIP recording architecture
                                                                                       EDUCATI...
VRS network attached
                                                                     EDUCATION



• VRS combines VoIP...
VRS PBX attached
                                                                     EDUCATION



 • Proprietary interfac...
IP PBX functionality
                                                                     EDUCATION



• Auto attendant: d...
VoIP protocols
- ITU and IETF                                                       EDUCATION




• Gateway control: MGCP,...
Contact center statistics
                                                                     EDUCATION




• Avg. contac...
VoIP network loading
                                                                     EDUCATION




• Depends on
     ...
VoIP recording agenda
                                                                     EDUCATION




• Voice recording...
Data center surprise
                                                                     EDUCATION




• Many start 100% ...
VoIP storage tiers
                                                                                               EDUCATIO...
VoIP voice recording
                                                                      EDUCATION



 • File or databas...
Call detail record
                                                                     EDUCATION




• Typically cut by I...
VoIP storage tier I
                                                                     EDUCATION




• 0-7 days
• Real t...
VoIP storage tier II
                                                                     EDUCATION




• 7 to 90 or 180 d...
VoIP storage tier III
                                                                     EDUCATION




• > 90 or 180 day...
VoIP voice SAN loading
                                                                     EDUCATION




• ~150GB/day rec...
Storage H/W
                                                                     EDUCATION




• Tier I - usually direct a...
VoIP disaster recovery
considerations                                                       EDUCATION




• Analog PBX equ...
VoIP recording agenda
                                                                     EDUCATION




• Voice recording...
Voice recording
data mining activities                                               EDUCATION



• Identify call and busi...
Speech Analytics
                                                                     EDUCATION




• Keyword spotting
   ...
Speech keyword spotting
                                                                     EDUCATION




• Transcribes c...
Voice emotion analysis
                                                                     EDUCATION




• Scores caller ...
Talk pattern analysis
                                                                     EDUCATION




• Scores call tal...
Voice print identifier
                                                                     EDUCATION




• Biometric voic...
Speech search engine
                                                                     EDUCATION



 Based on vocabular...
Speech recognition
                                                                     EDUCATION



•    Trained vs. untr...
Q&A / Feedback
                                                                                                    EDUCATI...
Upcoming SlideShare
Loading in …5
×

VOIP recodring fro competitive advantage

428 views
387 views

Published on

0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
428
On SlideShare
0
From Embeds
0
Number of Embeds
1
Actions
Shares
0
Downloads
6
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

VOIP recodring fro competitive advantage

  1. 1. EDUCATION Business Intelligence From Mining VoIP Voice Recordings Ray Lucchesi, Silverton Consulting, Inc.
  2. 2. SNIA Legal Notice EDUCATION • The material contained in this tutorial is copyrighted by the SNIA. • Member companies and individuals may use this material in presentations and literature under the following conditions: – Any slide or slides used must be reproduced without modification – The SNIA must be acknowledged as source of any material used in the body of any document containing material from these presentations. • This presentation is a project of the SNIA Education Committee. Business Intelligence From Mining VoIP Voice Recordings © 2 2007 Storage Networking Industry Association. All Rights Reserved.
  3. 3. Abstract EDUCATION Business Intelligence From Mining VoIP Voice Recordings Today the convergence of telephony and the digital world due to the VoIP changeover is creating unprecedented opportunities to exploit and mine voice data not readily available before. Our presentation will describe technology used to record VoIP voice calls and detail typical storage architectures for voice storage. We conclude with how to mine voice recordings using keyword spotting, phonetic search, and other technology readily available today and discuss future voice recognition trends. Business Intelligence From Mining VoIP Voice Recordings © 3 2007 Storage Networking Industry Association. All Rights Reserved.
  4. 4. VoIP recording agenda EDUCATION • Voice recording architecture • Voice recording storage • Voice recording data mining Business Intelligence From Mining VoIP Voice Recordings © 4 2007 Storage Networking Industry Association. All Rights Reserved.
  5. 5. VoIP architecture EDUCATION IP Media PBX Gateway PSTN Media Gateway - translates from switched phone to VoIP IP PBX - VoIP public branch exchange Business Intelligence From Mining VoIP Voice Recordings © 5 2007 Storage Networking Industry Association. All Rights Reserved.
  6. 6. VoIP adoption EDUCATION • Predicting >50% of enterprise PBX’s to be VoIP by 2008 • Y2K caused companies to upgrade call centers - Many now coming off lease/fully depreciated • VoIP latest technology – Inexpensive – Convergent to digital – QOS improving – Open standards available – Increasing vendor support Business Intelligence From Mining VoIP Voice Recordings © 6 2007 Storage Networking Industry Association. All Rights Reserved.
  7. 7. Why companies record voice EDUCATION • Quality assurance – “…this call may be recorded for quality assurance purposes…” • Compliance – DOT requires all transportation company complaints to be recorded and listened to within 6 months • Data mining – Data mining requirements may change over time and can re-mine same data Business Intelligence From Mining VoIP Voice Recordings © 7 2007 Storage Networking Industry Association. All Rights Reserved.
  8. 8. Legal Concerns EDUCATION • USA allows recording calls – 38 states if one party provides authorization, “one- party consent” – 12 states if all parties on the call provide authorization, “two-party consent” • California, Connecticut, Florida, Illinois, Maryland, Massachusetts, Michigan, Montana, Nevada, New Hampshire, Pennsylvania and Washington. • International varies by jurisdiction Business Intelligence From Mining VoIP Voice Recordings © 8 2007 Storage Networking Industry Association. All Rights Reserved.
  9. 9. VoIP recording architecture EDUCATION IP Media VRS PBX Gateway PSTN VRS VRS - Voice recording system Business Intelligence From Mining VoIP Voice Recordings © 9 2007 Storage Networking Industry Association. All Rights Reserved.
  10. 10. VRS network attached EDUCATION • VRS combines VoIP packets into call voice recording • Configure voice traffic through one switch and VLAN • Switch duplicates voice traffic to VRS server – VRS has packet sniffer at Span Port – Remote sites echo traffic back to switch • Works with any IP PBX Business Intelligence From Mining VoIP Voice Recordings © 10 2007 Storage Networking Industry Association. All Rights Reserved.
  11. 11. VRS PBX attached EDUCATION • Proprietary interface to VRS system or VRS onboard PBX • Possibly proprietary voice recording format • IP PBX proprietary data available Business Intelligence From Mining VoIP Voice Recordings © 11 2007 Storage Networking Industry Association. All Rights Reserved.
  12. 12. IP PBX functionality EDUCATION • Auto attendant: dial by name, extension, or group, ACD, CCR • Voicemail: security, multiple greetings & mailboxes, vmail review, forwarding, notification & email • Conferencing: public & private, recording, conference admin. • Others: call park, hold, & xfer, hunt groups, speed dial, remote ofc, call logs & detail records • Music Business Intelligence From Mining VoIP Voice Recordings © 12 2007 Storage Networking Industry Association. All Rights Reserved.
  13. 13. VoIP protocols - ITU and IETF EDUCATION • Gateway control: MGCP, SGCP,IPDC, MEGACO • Signaling: H-323, H-225, H-235, H-245, H-450, T-38, T-120 • Session: SIP, SDP, SAP • Media transport: RTP, RTCP, RTSP • Media encoding: G.711, G.722, G.723, G.726, G.727, G.729 Business Intelligence From Mining VoIP Voice Recordings © 13 2007 Storage Networking Industry Association. All Rights Reserved.
  14. 14. Contact center statistics EDUCATION • Avg. contact center ~10M calls/year, 500-1000 operators • Avg. call ~3-5 minutes, but length industry and call center driven • Not unusual to have 5000 operator call center in Asia, US call centers smaller Business Intelligence From Mining VoIP Voice Recordings © 14 2007 Storage Networking Industry Association. All Rights Reserved.
  15. 15. VoIP network loading EDUCATION • Depends on – CODEC, ranging from 5.3 to 64Kbps - impacts QOS – Number of active voice lines • For 100 active lines – 1.6 Mbps using G.723.1 CODEC – 8.0 Mbps using G.711 CODEC Business Intelligence From Mining VoIP Voice Recordings © 15 2007 Storage Networking Industry Association. All Rights Reserved.
  16. 16. VoIP recording agenda EDUCATION • Voice recording architecture • Voice recording storage • Voice recording data mining Business Intelligence From Mining VoIP Voice Recordings © 16 2007 Storage Networking Industry Association. All Rights Reserved.
  17. 17. Data center surprise EDUCATION • Many start 100% call recording to enterprise class disk • Quickly discover TB/month of disk tied up, then move to Tier II • Still find ~10s TB/yr too expensive for Tier II then move to Tier III • Finally move from saving 100% of calls to saving only select calls Business Intelligence From Mining VoIP Voice Recordings © 17 2007 Storage Networking Industry Association. All Rights Reserved.
  18. 18. VoIP storage tiers EDUCATION Media IP Tier I VRS Gateway PBX 0-7 days PSTN Tier I 0-7 days Tier II 7- 90 or 180 days Tier III > 90 or 180 days Business Intelligence From Mining VoIP Voice Recordings © 18 2007 Storage Networking Industry Association. All Rights Reserved.
  19. 19. VoIP voice recording EDUCATION • File or database entries • Raw file (1-15MB) depending on call length & VoIP CODEC • VRS can convert CODEC to standard media format – .WAV, .MP3, etc. – ~1MB/call minute • Created and read sequentially • Tier I recordings done in real time Business Intelligence From Mining VoIP Voice Recordings © 19 2007 Storage Networking Industry Association. All Rights Reserved.
  20. 20. Call detail record EDUCATION • Typically cut by IP PBX system • Includes: caller-id, number called, time-date stamp, call duration, etc. • Can include PBX info: operator-id, customer-id, operator login time, etc. • Periodic screen shots of operator screen • Not that large • Used as cross index to voice recording Business Intelligence From Mining VoIP Voice Recordings © 20 2007 Storage Networking Industry Association. All Rights Reserved.
  21. 21. VoIP storage tier I EDUCATION • 0-7 days • Real time sequential write access • For average call center – ~3.3TB of voice recordings/month – ~833K voice files or entries/month – ~833K call detail files/month ∑ ~1.7M files/month Business Intelligence From Mining VoIP Voice Recordings © 21 2007 Storage Networking Industry Association. All Rights Reserved.
  22. 22. VoIP storage tier II EDUCATION • 7 to 90 or 180 days • SAN or NAS storage • Sequential, read mostly • For QA ~1-3% of voice recordings accessed/month • For Compliance up to 100% voice recordings accessed/month • Discarding some un-needed files Business Intelligence From Mining VoIP Voice Recordings © 22 2007 Storage Networking Industry Association. All Rights Reserved.
  23. 23. VoIP storage tier III EDUCATION • > 90 or 180 days • Access rates un-quantifiable but << 1%/month • Call metadata used to determine – How much to retain long term? – How long to retain voice recordings? - typical 7 yrs Business Intelligence From Mining VoIP Voice Recordings © 23 2007 Storage Networking Industry Association. All Rights Reserved.
  24. 24. VoIP voice SAN loading EDUCATION • ~150GB/day recording load for Tier I – Real-time, high sequential write workload • ~4.5GB/day QA-listening load for Tier II • Add data movement - Tier I to II and Tier II to III • Add compliance listening load for Tier II Business Intelligence From Mining VoIP Voice Recordings © 24 2007 Storage Networking Industry Association. All Rights Reserved.
  25. 25. Storage H/W EDUCATION • Tier I - usually direct attached but can use enterprise class SAN storage • Tier II - less expensive than enterprise class • Tier III - archive appliances, tape library, or optical jukebox Business Intelligence From Mining VoIP Voice Recordings © 25 2007 Storage Networking Industry Association. All Rights Reserved.
  26. 26. VoIP disaster recovery considerations EDUCATION • Analog PBX equipment caused distinct DR plans • VoIP bringing call center DR plans back inside data center • Higher network requirements to support VoIP Business Intelligence From Mining VoIP Voice Recordings © 26 2007 Storage Networking Industry Association. All Rights Reserved.
  27. 27. VoIP recording agenda EDUCATION • Voice recording architecture • Voice recording storage • Voice recording data mining Business Intelligence From Mining VoIP Voice Recordings © 27 2007 Storage Networking Industry Association. All Rights Reserved.
  28. 28. Voice recording data mining activities EDUCATION • Identify call and business trends – Flood of calls traced to minor website change • Improve business processes and products – Product trends detected sooner • Tag calls for further review – Disgruntled customer scheduled for follow-up special offers • Detect caller fraud – Biometric id of person calling based on prior calls • Speech search engine Business Intelligence From Mining VoIP Voice Recordings © 28 2007 Storage Networking Industry Association. All Rights Reserved.
  29. 29. Speech Analytics EDUCATION • Keyword spotting – Limited vocabulary identified • Emotion analysis – Caller stress level assessed • Talk pattern analysis – Call tempo analyzed Business Intelligence From Mining VoIP Voice Recordings © 29 2007 Storage Networking Industry Association. All Rights Reserved.
  30. 30. Speech keyword spotting EDUCATION • Transcribes call into XML file using limited vocabulary • Done mostly offline in post process • Determines voice record processing options • Experiments in real-time word spotting at state of the art call centers • Used to spot product call trends or other keywords of interest Business Intelligence From Mining VoIP Voice Recordings © 30 2007 Storage Networking Industry Association. All Rights Reserved.
  31. 31. Voice emotion analysis EDUCATION • Scores caller stress level • Determines voice recording processing options • Done in post processing step • Experiments in real-time stress analysis at state of the art call centers • Used to spot disgruntled/stressed callers Business Intelligence From Mining VoIP Voice Recordings © 31 2007 Storage Networking Industry Association. All Rights Reserved.
  32. 32. Talk pattern analysis EDUCATION • Scores call talk pattern by identifying tempo, turn-taking, other conversation dynamics, and parts of call • Determines voice recording processing options • Done post processing • Used mostly for quality assurance Business Intelligence From Mining VoIP Voice Recordings © 32 2007 Storage Networking Industry Association. All Rights Reserved.
  33. 33. Voice print identifier EDUCATION • Biometric voice print from prior call general speech or from “pass phrase” • Comparison made at next call to authenticate person speaking • Done in real-time • Used as a substitute PIN/Password or as alternate way to validate persons identity Business Intelligence From Mining VoIP Voice Recordings © 33 2007 Storage Networking Industry Association. All Rights Reserved.
  34. 34. Speech search engine EDUCATION Based on vocabulary or phonetics • Large vocabulary continuous speech recognition (LVCSR) advantages – Better accuracy – Transcription available – Storage efficient • Phonetics advantages – Unlimited vocabulary – No re-processing for new keywords – Multi-language support – Faster indexing Business Intelligence From Mining VoIP Voice Recordings © 34 2007 Storage Networking Industry Association. All Rights Reserved.
  35. 35. Speech recognition EDUCATION • Trained vs. untrained • Continuous vs. paused speech • Controlled vs. uncontrolled channel • Interactive vs. passive • Limited vs. unlimited vocabulary 50-80% accurate today • Predicting better than human recognition by 2011 • Accuracy can improve through – Better software and systems – More processing power devoted to analyzing call Business Intelligence From Mining VoIP Voice Recordings © 35 2007 Storage Networking Industry Association. All Rights Reserved.
  36. 36. Q&A / Feedback EDUCATION • Please send any questions or comments on this presentation to SNIA: trackapplications@snia.org Many thanks to the following individuals for their contributions to this tutorial. SNIA Education Committee Raymond Lucchesi Business Intelligence From Mining VoIP Voice Recordings © 36 2007 Storage Networking Industry Association. All Rights Reserved.

×