Conversational Technologies

27/11/2018

I'm very excited to be speaking at the Conversational Interaction conference in March in San Jose (http://www.conversationalinteraction.com/). I'll be talking about "Resources and tools for natural language design: intents and entities". Although there are some great natural language application development toolkits around, they assume that you pretty much know how your application will be structured -- that is, what intents and entities you want to use in your application. I don't think that's typically the case, and making a mistake on the application structure at the beginning can lead to a lot of rework later on. I first talked about how to find the right intents and entities at the Voice Summit last July in Newark (https://www.voicesummit.ai/) Here's my presentation (http://www.conversational-technologies.com/presentations/voice2018.pdf). At Conversational Interaction I'll continue on with this topic with much more detail.

HOME

04/06/2018

I'm excited to be speaking at on July 24-26 in Newark, NJ. Join me and the community to explore the voice ecosystem and how it's impacting your industry. Use CODE:
TalkVoice2Me for 10% off your ticket: http://bit.ly/2wLGKQA

VOICE is a three-day summit at the forefront of natural language processing. VOICE, sponsored by Amazon Alexa, will be held at the New Jersey Institute of Technology July 24-26. Natural language is revolutionizing the way we interact with devices, services, products and one another. VOICE is where t...

02/05/2018

What if you combined , , and other services in applications? Come to my free online talk sponsored bye on June 5 to find out. Register here https://www.eventbrite.com/e/integrating-speech-with-intelligent-services-tickets-45351046200

We are currently experiencing an explosion of sophisticated, cloud-based intelligent services. There are several well-known speech and natural language services, but other cognitive technologies are fast becoming available as cloud services. These include face recognition, emotion recognition, trans...

02/05/2018

08/12/2016

My book on standards for multimodal interaction is finally out! It includes 19 chapters on such topics as the W3C Multimodal Architecture, voice standards, and EmotionML, written by experts in their areas. More information at http://www.springer.com/us/book/9783319428147. I hope this can inspire developers who want to use multimodal technologies like speech, natural language, gesture and vision to use a standards-based approach.

This book presents new standards for multimodal interaction published by the W3C and other standards bodies in straightforward and accessible language,...

04/01/2016

"Speech and Language Technologies for Language Disorders" (co-authored with Katharine Beals, Marcia Linebarger and Ruth Fink) is finally out!
http://www.amazon.com/dp/1614517584/ref=tsm_1_fb_lk. I hope it will be useful for people with family members who have a language disorder as well as for speech and language pathology professionals.

Speech and Language Technology for Language Disorders (Speech Technology and Text Mining in Medicine and Health Care)

02/12/2015

Finally finishing up "Speech and Language Technologies for Language Disorders"! It should be available in December http://www.degruyter.com/view/product/284563?rskey=oEVrTQ&result=1

This book draws on the recent remarkable advances in speech and language processing: advances that have moved speech technology beyond basic applications such as medical dictation and telephone self-service to increasingly sophisticated and clinically significant applications aimed at complex speech…

19/08/2015

I'm having a great time at SpeechTek www.speechtek.com in New York. Looking forward to today's track on the Internet of Things and my talk on Natural Language and the Internet of Things.

This year, SpeechTEK is turning 20! Through the years, we've seen so many exciting changes in the industry, from the 90's when ASR was first made available to consumers and the first IVR from BellSouth was introduced, to today, when we can speak to our computers, phones, cars, and more. We've witne…

09/07/2015

There's a new charter for the W3C Multimodal Interaction Working Group (http://www.w3.org/2002/mmi/. Exciting new work on component discovery for dynamic systems, (very important for the Web of Things) and a new version of EMMA that addresses system output. See the announcement https://lists.w3.org/Archives/Public/www-multimodal/2015Jul/0002.html

The Multimodal Interaction Activity seeks to extend the Web to allow users to dynamically select the most appropriate mode of interaction for their current needs, including any disabilities, while enabling developers to provide an effective user interface for whichever modes the user selects. Depend…

17/06/2015

I'm very excited to be starting a new book project, "Multimodal Interaction with W3C Standards: Towards Natural User Interfaces to Everything". It's going to be an edited book with contributed chapters about standards for interacting with technology using speech, handwriting and other forms of natural interaction. See the book website, www.mmi-standards.com for more information.

From tiny fitness trackers to huge industrial robots, we are interacting today with devices with shapes, sizes, and capabilities that would have been hard to imagine when the traditional graphical user interface (GUI) first became popular in the 1980’s. It is becoming increasingly apparent that the…

11/06/2015

Here's a video demo I made of multilingual speech recognition in the browser https://youtu.be/S-6fIA2U2R4 showing some basic speech recognition concepts. Try it yourself www.proloquia.com/speechDemo.html!

This is a demo of multilingual speech recognition in the browser using the Web Speech API and EMMA. It shows speech recognition concepts like nbest and confi...

12/05/2015

I recently helped some EE students with ideas for using speech in electrical engineering applications that they were doing for a class project. Here's the hands-free, voice-enabled electrical data recorder that they built https://www.youtube.com/watch?v=8jpuOPidJiw

ECE 473 Spring 2015 Final Project Are you tired of putting down your multimeter probes to record a measurement, only to forget the value by the time you pick...

28/04/2015

Here are some slides on a recent talk I gave on Web accessibility for people with cognitive disabilities.

Web Accessibility for People with Cognitive Disabilities Deborah Dahl, Ph.D. Principal, Conversational Technologies Member, W3C Cognitive Accessibility Task Fo…

26/03/2015

I'm looking forward to this year's Mobile Voice Conference (http://mobilevoiceconference.com/) in San Jose, April 20-21. I'll be speaking on "Natural Language Interaction with the Web of Things". Have you ever wondered how people are supposed to interact with all those cool new connected devices like light bulbs, appliances, dog collars, medical sensors and, well, everything? Apps? Fine if there are only a few devices, but what happens when the Internet of Things takes off and these things are everywhere? Will you have thousands of apps? That can't work!

The maturing of speech and natural language technology is changing user expectations of the ease of interacting with increasing numbers of devices, applications, services, and features - “digital overload.” Mobile devices make this intuitive connection with computers always available. The Mobile Voi…

24/03/2015

On April 17, I'll be speaking at EvoHax (http://www.evohax.com/), an accessibility hackathon in Philadelphia, on "Web Accessibility for People with Cognitive Disabilities). I'll talk about cognitive accessibility in general, as well as the recent activities of the W3C Task Force on Cognitive Accessibility (http://www.w3.org/WAI/PF/cognitive-a11y-tf/).

evoHaX will bring together students from various universities around Philadelphia to develop web accessibility solutions in a 24-hour-long Hackathon. The event will focus on creating awareness about web accessibility among student developers, and tackling the challenges people with disabilities face…

16/09/2014

On September 24, I'll be speaking in a Forrester Research webinar on the New Engagement Workplace, talking about how W3C standards can simplify pervasive mobile collaboration within the enterprise https://event.on24.com/eventRegistration/EventLobbyServlet?target=reg20.jsp&eventid=850031&sessionid=1&key=338BCB27C01D9F348791C9FD761F2A9F&sourcepage=register
Please join me if you're interested in this topic!

27/08/2014

SpeechTEK 2014 in New York was stimulating and exciting, with a lot of innovative technologies being presented. Some of the hot topics were wearables, robots, virtual assistants and the connected home. Many of the presentations are now online at http://www.speechtek.com/2014/Presentations.aspx, including my presentations, "Use Speech and Language Technologies to Overcome Language Disorders" and "Develop Multimodal Applications With Free and Open Source Tools".

13/08/2014

I'm very honored to have received a Speech Luminary Award from Speech Technology Magazine this year, for my work on speech standards, especially for helping move Emotion Markup Language ( http://www.w3.org/TR/emotionml/) through the standardization process. I hope this helps bring Emotion Markup Language and other speech and multimodal standards, to more people's attention. The article is at http://www.speechtechmag.com/Articles/Editorial/Cover-Story/2014-Speech-Industry-Awards-98321.aspx.

Copyright © 2014 W3C® (MIT, ERCIM, Keio, Beihang), All Rights Reserved. W3C liability, trademark and document use rules apply.

20/06/2014

I've been at the SIGDIAL conference (Special Interest Group on Discourse and Dialog, http://www.sigdial.org/workshops/conference15/) for the past couple of days. Some interesting themes have been open domains, unsupervised learning, affective systems, and a common evaluation task on dialog state tracking. Also, great networking and a fantastic Chinese banquet at Joy Tsin Lau in Philadelphia.