Spoken Dialogue Analytics
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 effort and expertise. A significant portion of this effort is geared towards the development of the domain semantics and associated grammars, system prompts and spoken dialogue call-flow.
We propose a semi-automated process for spoken dialogue service development and speech service enhancement of deployed services, where incoming speech service data are semi-automatically transcribed and analyzed (human-in-the-loop).
A list of mature technologies will be used to
Specifically the technologies used will be: grammar induction, text-mining for language modeling, affective modeling of speech and text data, machine translation, crowd-sourcing, speech recognition/transcription, ontology induction. The technologies will be integrated in a service doctoring platform that will enhance deployed services using the human-in-the-loop paradigm.
Our business model is quick deployment of a prototype service, followed by service enhancement using our semi-automated service doctoring 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 for SME in the services area with little expertise in speech service development (B2B) and also end-user that are developing their own in house speech service often with limited success (B2C).
SpeDial is built around the knowledge cascade of technologies, data and services. Automatic or machineaided algorithms will be used to analyze the data logs from deployed speech services, and, in turn, these data will be used to tune in a cost-effective manner the speech service using the set of algorithms and tools of the SpeDial platform.
The main S&T goal of SpeDial is to devise machine-aided methods for spoken dialogue system enhancement and customization for call-center applications. SpeDial adopts a user-centric approach to SDS design. Rather than simply rolling out algorithms from the research lab to the real world (being hopeful about their usefulness), we have tried to map the requirements of a speech services developer and emulate the logical flow being followed.
In this process, we have identified two scenarios: service enhancement where the developer starts from an existing application and tries to improve KPI performance and user satisfaction, and service customization where the developer addresses the special needs of a user population. Thus our second goal is to create a platform that supports cost-effective service doctoring for those two scenarios: enhancement and customization. The platform also include interfaces for service and user satisfaction monitoring (IVR analytics component).
Our third goal is to create and support a sustainable pool of developers that will be trained to use the platform. Two separate groups of users are targeted: non-commercial users including the research community and speech services developers at end-user companies. All in all, SpeDial has ambitious but realistic goals both for technological and commercial exploitation of project outputs.
Telecommunication Systems Research Institute (T.S.I.)
Technical University of Crete
Campus – Akrotiri
Click on the different category headings to find out more. You can also change some of your preferences. Note that blocking some types of cookies may impact your experience on our websites and the services we are able to offer.
Because these cookies are strictly necessary to deliver the website, you cannot refuse them without impacting how our site functions. You can block or delete them by changing your browser settings and force blocking all cookies on this website.
If you do not want that we track your visist to our site you can disable tracking in your browser here:
We also use different external services like Google Webfonts, Google Maps and external Video providers. Since these providers may collect personal data like your IP address we allow you to block them here. Please be aware that this might heavily reduce the functionality and appearance of our site. Changes will take effect once you reload the page.
Google Webfont Settings:
Google Map Settings:
Vimeo and Youtube video embeds: