DialogCONNECTION Limited is the brainchild of Dr. Maria Aretoulaki.
Maria has been working on Automatic Speech Recognition (ASR) applications, Speech IVRs and Voice User Interfaces (VUIs) since 1996. She has specialised in user-centred but robust VUI design for Call Centre automation and in adaptive error recovery strategies for mixed-initiative dialogues, focusing on spontaneous speech. She has also been working on IVR persona design and dialogue scripting, usability testing and IVR tuning for several industries and languages. In addition to her technical expertise, Maria has also acquired considerable experience in People and Project Management for Speech and Multimodal projects.
Maria has held senior positions with several speech companies: She has been Head of Speech Design at Vicorp (UK), Head of Dialogue Development at SemanticEdge (Germany), Project Manager at the Bavarian Research Centre for Knowledge-based Systems (FORWISS) and one of the founders of the spinoff company Sympalog (Germany). She has also worked as an independent Speech / Voice Consultant through the Gerson Lehrman Group’s Councils of Technology Advisors, Maven, Convetit and Raytheon BBN Technologies (US), the European Commission (Belgium), VoxGen / 8Hertz (Germany / UK) and KCOM / JamIP (UK); as a VUI Designer at Convergys / Intervoice (UK and US) and at Clarity AG (Germany), and as an EU Post-Doctoral Fellow at the University of Erlangen-Nuremberg (Germany). Through DialogCONNECTION, she has been working on projects for multinationals in the Tech, Insurance and Security industries, large Telecoms, Utilities, Insurance, Speech Software providers and the Government in the UK, Telecoms in Switzerland and Speech platform providers in Greece. She has designed voice-enabled or speech-activated services as diverse as telephone banking systems, Government and Tech Helplines, shop locators and voice memos for many different countries from the UK, to Germany, Austria, Switzerland, France, Greece, and the US. DialogCONNECTION was also awarded by the European Commission an EU FP7 3-year R&D grant to develop an automated Call Centre Agent Training system in the context of the METALOGUE project (2013-16).
Originally from Greece, Maria has spent the last two decades between the UK and Germany, and speaks English, German, French and Greek fluently. Due to her classical education and her Latin, she also understands Italian, Spanish and Portuguese too.
Maria holds a BA (Hons) in Linguistics & English from The University of Athens (Greece), an MSc in Machine Translation and a PhD in Automatic Text Summarisation & Language Engineering from the University of Manchester (UK). She has also held a Post-Doctoral Fellowship on Spoken Dialogue Management at the University of Erlangen-Nuremberg (Germany) funded by the EU Human Capital Mobility Programme.
She has (co-)authored
several publications, including the Chapter on Spoken Dialogue Systems
in the Oxford University Press textbook "Handbook of Computational Linguistics".
She has served in several Advisory Committees for dialogue-related
projects and in the Review Panels of International Conferences and
Scientific Journals in Computer Science, and Language & Speech
Processing. She is also a member of a number of scientific, business and
digital societies. In the past few years, Maria has been contributing
to the SpeechTEK specialist Conference with presentations on VUI Design issues and Best Practices, topics that she also discusses in her Wordpress Blog. In May 2011, Maria co-chaired the Workshop on "Cross-linguistic & Cross-cultural Voice Interaction Design" organised by the Association for Voice Interaction Design (AVIxD) and the Applied Voice Input/Output Society (AVIOS). She presented the results of the workshop at SpeechTEK Europe 2011 in London the following day, where she was also one of the “5 global speech tech experts” taking part in the Meet the Consultants Clinic.
In 2012, Maria was invited to give a talk at TEDxManchester on Voice Recognition (FTW!).
She spoke about the weird and wonderful world of Voice Recognition, from the inaccurate – and far too often funny – simple voice-to-text apps
and dictation systems on your smartphones, to the most frustrating
automated Call Centres, to the next generation, sophisticated SIRI and Google Assistant, and everything in-between. She explained why things go wrong and when things can go wonderfully right. The answer is “CONTEXT”;
the more you have of it , the more accurate and relevant the
interpretation of user intention will be, and the more relevant and
impressive the system reaction / reply will be. and you can watch it on YouTube here.
You can also find Maria's comprehensive reports on both TEDxSalford 2012 and TEDxManchester 2012 in her blog.