SpeDial:
Machine-Aided Methods for Spoken Dialogue System Enhancement and Customization for Call-Center Applications
 

The speech services industry has been growing both for telephony applications and, recently, also for smartphones (e.g., Siri). Despite recent progress in spoken dialogue system (SDS) technologies the development cycle of speech services still requires significant manual effort and expertise. A significant portion of this effort is geared towards the optimization of dialogue call-flow, grammars and prompts of deployed services to reach target key performance indicators (KPIs). We propose a process for spoken dialogue service development, enhancement and customization of deployed services, where data logs are analyzed and used to enhance the service in a semi-automated fashion. A list of mature technologies will be used to: 
  1. identify hot-spots in the dialogue and propose alternative call-flow structures, 
  2. select among list of prompts to reach target KPIs, 
  3. update grammars using transcribed service data and 
  4. customize application for specific user populations. 

Specifically, the list of technologies used will be: affective modeling of spoken dialogue, call-flow/discourse analysis, machine translation, crowd-sourcing, grammar induction, user modeling. The technologies listed above will be integrated in a service-doctoring platform that will enhance deployed services. Our business model is quick deployment of a prototype service, followed by service enhancement using our platform. The reduced development time and time-to-market will provide significant differentiation for SME in the speech services areas, as well as, end-users. The business opportunity is significant especially given the consolidation of the speech services industry and the lack of major competition. Our offering is attractive to SME in the services area with little expertise in speech service development (B2B) and also end-users that are developing their own in house speech service often with limited success (B2C).


Recent Announcements

  • 2nd Year Review, Luxembourg, January 2016 The second year review will take place in Luxembourg on January 14th, 2016.(a preparatory technical meeting will take place in Luxembourg on January 13, 2016)
    Posted Dec 28, 2015, 1:57 PM by Elias Iosif
  • AfricaCom in Johannesburg, South Africa VoiceWeb participated as an exhibitor and presented SpeDial to African companies that are potential early adopted of such solutions - November 2015
    Posted Dec 28, 2015, 1:54 PM by Elias Iosif
  • Electrica's Smart Metering Event in Sibiu, Romania VoiceWeb participated at the eventorganised by Electrica SA as an exhibitor along with its romanian partner and discussed the importance of the customer service in the utilities companies - November 2015
    Posted Dec 28, 2015, 1:53 PM by Elias Iosif
  • ICT 2015 Lisbon, Portugal INESC-ID participated at the event and presented SpeDial to the participants - October 2015
    Posted Dec 28, 2015, 1:52 PM by Elias Iosif
  • Gitex Technology Week in Dubai, UAE VoiceWeb’s representatives visited the event and discussed the with its partners and potential clients the added benefit of personalization and automation in speech analytics - October 2015
    Posted Dec 28, 2015, 1:50 PM by Elias Iosif
Showing posts 1 - 5 of 19. View more »