1 / 15

TEL500-Voice Communications IVR using Speech Recognition in Asterisk Devesh Mendiratta

TEL500-Voice Communications IVR using Speech Recognition in Asterisk Devesh Mendiratta Sameer Deshmukh & Srinivas Madlapelli. Outline. Introduction Flow Chart Google API Google API Interface with Asterisk Results Applications Conclusion Resources References. Introduction.

hada
Télécharger la présentation

TEL500-Voice Communications IVR using Speech Recognition in Asterisk Devesh Mendiratta

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. TEL500-Voice Communications IVR using Speech Recognition in Asterisk Devesh Mendiratta SameerDeshmukh & SrinivasMadlapelli

  2. Outline • Introduction • Flow Chart • Google API • Google API Interface with Asterisk • Results • Applications • Conclusion • Resources • References

  3. Introduction • Responses as per the input provided by User • Speech to Text Technique • c0dE: Interface of Google API (Application Programming Interface) with Asterisk • Queues • Playback the recordings

  4. Flow Chart

  5. Google API Syntax : same => n,agi(googletts.agi,text,[language],[intkey]) • Text field • Language field • Intkey field

  6. Speech agi Syntax: Same => n(record),agi(speech-recog.agi,[lang],[timeout],[intkey],[NOBEEP])

  7. Google agi with Asterisk same => n(record),agi(speech-recog.agi,en-US) same => n,Verbose(1,Script returned: ${status} , ${id} , ${confidence} , ${utterance}) same => n,GotoIf($["${utterance}" = "business"]?sales:recheck) same => n(sales),Background(withusa)

  8. Cont. same => n(sales),Goto(queues,801,1) same => n(recheck),GotoIf($["${utterance}" = "support"]?support:retry) same => n(support),Background(withusu) same => n,Goto(queues,802,1) same => n(retry),Background(repeat) same => n,agi(googletts.agi,"Can you please repeat more clearly?",en) same => n,goto(record)

  9. Results – Sales Queue Execution

  10. Results – Support Queue Execution

  11. Applications • Can be extended by including all possible options • Typical Example – AT&T • Account Recharge- Credit/Debit Card • Balance check • Customer Assistance • Surveys • Campaigning

  12. Conclusion • Support to all types of Businesses • “Simple design” approach • Service specific, e.g. Ordering Pizza via Phone

  13. Resources • Hardware : 3 SIP phones • Interface Files : speech-recog.agi & googletts.agi • Installation : perl-libwww, the WWW library for Perl

  14. References • http://www.nuance.com/for-individuals/by-solution/speech-recognition/index.htm • http://zaf.github.io/asterisk-speech-recog/

  15. Any Questions ?

More Related