Events Add an event Speakers Talks Collections
 
MLconf Online 2020
November 6, 2020, Online
MLconf Online 2020
Request Q&A
MLconf Online 2020
From the conference
MLconf Online 2020
Request Q&A
Video
Voice Assistants in Healthcare
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Add to favorites
40
I like 0
I dislike 0
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
  • Description
  • Transcript
  • Discussion

About the talk

Voice Assistants, such as Siri, Alexa, and Google Assistant have become increasingly commonplace in the consumer setting. Their functionality continues to improve, and they are setting the bar for user experience in many industries, including Healthcare.

Healthcare IT systems that support members and providers are diverse and often tightly coupled with legacy systems that struggle to catch up with the latest technologies. Chatbots deployed via web portals and mobile apps, call centers systems, as well as Amazon Echo and Google Home devices are all examples of channels through which information can be delivered to members and providers. It is very important to ensure that this information is the same irrespective of the channel and that the user experience is at least similar with each channel.

This presentation will introduce the reference architecture and implementation that supports the above strategy. We implement our systems as pipelines of swappable components; and we connect them together based on the requirement of the particular system. Some of these components can be based on commercial services, others, based on Open Source technologies.

We will then specifically focus on implementing Voice / NLP systems powered by machine and deep learning technologies that improve over time. We will cover data annotation tooling, best practices for incremental dataset collection and management, model retraining, overall CI / CD for services and models.

About speaker

Galina Grunin
Distinguished Engineer at Optum

Galina Grunin is a Distinguished Engineer in the Advanced Technology Collaborative team at Optum, UnitedHealth Group, with a focus on Deep Learning. She is a hands-on IT practitioner with expert knowledge and experience in deep learning, orchestration and pattern deployment, cloud computing architecture, software-defined storage, software-defined networking, adapting legacy systems for cloud, web technologies, and application and middleware integration. Galina’s achievements in the above fields are recognized by over 40 U.S. patents in which Galina is a named inventor. Prior to joining Optum, Galina was the lead architect/technical lead for various projects at IBM Cloud and IoT divisions.

View the profile
Share

Hello. I'm a need you to this engineer at the Optum. And them. It was uniquely positioned to actually deliver on that promise. We are able to deliver one person at a time. And the center of our business is all data and analytics and Healthcare the drive-in size for a more competitive view of the solar system. Open Twitch for Tyson able to create a holistic view in shooting. The patient is getting the most accurate Healthcare Footprints, in local Healthcare and Family Services.

And its course. All consuming speak instructions. I don't know if I did, I just Air products and services. At least we see our three business units and Optum RX. I got something for your able to sort of manifestations of the cell system Hospital, life science of musician, employees and consumers, are spending it alone us to push connections and efficiency in the way that the scarf to match. Learn how to spell Fortune. 500 companies are government agents

include in all 50 states and the District of Columbia hospitals, approximately 8 to life, science or musician and 225 million consumers. Who are the size of them self and Optum RX will provide comprehensive solution for my expensive Health Care? You didn't the last weekend of them. Like I did in that way to cook Asian sizes and things became increasingly interested. But that patient care. What did you see in court? And improving the efficiency of style minimal,

lifestyle management, Hospital management. And last but not least. And you didn't reply back to previous episode from breaking new developments. Could you play Ignition by the clinical side between human speech production? The process of an abundance of what is types of data? How much is a Sports on Dish? The correct age of intercommunication response to the action and access customer satisfaction and then became available in the past few years making this possible to quickly. Try

out some Advanced deployment models from the Train application-specific. Open in the middle screen on the reading lights. Beta said sometimes, you can even use cases, specific date. The world. According to everybody using the cost of healthcare. It's very important to improve at my school Central. Using this new LP and SM kebabalicious. We can create a new social platform application. Personalized easy-to-use Channel voice, enable device. Implemented across a range of products and service providers in Asians

in Willoughby. Let's talk about practical example of school, Central application building conversation with a platform. Am I in this place to do an information to the island? This information is not to be system. Awesome information from this is the results and if you can provide information faster and sometimes more and be more focused on their Communications. An example of what year did scream today? I am a sorceress that produces text. Do the Texas. He's a sensible speech to your presentation of the day, which is played by the application back to the user

guide. Look up the music. Thunder cloud service. Our customers public loves you all fight tomorrow. Look up the address of the hard questions. Google show us in Jackson. What the model be able to understand medical terms? Advantages of using cloud services are not allowed to use them. System provides faster and more accurate response. Also,. Some customers are building our service in Torrance. Which I do models usually makes a publicly available and in college data. We do

something new set of some of these really simple, but very effective custom tools to help us create a new daughter for model, fight. You know, what the heck? It's about 24 hours to put you in different type of voice, different Age, Inquisition darwinopterus on how to pronounce them correctly. What's a good attitude to connecting the model in order to fight with you. How to connect a Galaxy photos from people's different voices on the grounds to use it as a golden fist. We came across

and not a problem, but no transcripts from 220. West Cesar mobile. Dim the collector training contesto, Dayton. Because we used to be the open 626 Rimrock in Sydney. Baby shark on all speakers include is you can see Richard pretty good results with a small amount of the publication's Pacific. The Google Voice Assistant pipeline is natural language processing. All next step is to be built in Italy model because the focus only use them for training phone called. Is there any idea which can be used for unsupervised Union?

What currency is used in local services. Are required linguistic features that approaches in Whitley Benton? Wisdom and knowledge in computer-wise abundance of available data on calls traded. I would like to cover what kind of essential to build up the voice assistant like intended action in the engine section in the motion detection. Also important. Let me listen to the song. This is also important. It is used to better understand text to extract facts that are not explicitly

mention. I love you someplace with services. What's the definition of a symptom of the. Which will be sent to the equation answering service? If you do see something related to the previous, the photo is the next best option at this point. We just passed the last component of the weather system pipeline. Dim the pictures. Text to speech, Thomas text or both of them. Weather going to be like in the most appropriate in cows, text to speech services, in improving quality, in the human voice, performance

and Friends. What develops application for the State of Texas in order to a customer who is today to the projects? We need to collect 24 hours open, April, Valencia. And I can look something up the voice with your address. One of the biggest challenge of the speech synthesis, since people generally do not like sticking to the machine is broken in spirit and energy speech segment time in limitation. Do you remember our sister is a spy planes over swappable components? We can make them to get the boys to the requirements of

particle system. What does a personal consultant? Lord? Where does a superlative is a deployment in the world? Is it into stimulant deployment of the new models? Wilson Trucking on completion of the deployment of data collection for the train for this guy, trying to build our pipeline that is applicable to different public clouds and can be used on Prime. If you have any questions, please. What is a factor? Fantastic presentation, me Lena. I think you're getting some wonderful Kudos here. Carlin rights in. It's very cool.

Is there any reason to do something like this for categorical predictors? Could you go to sleep remix? Candy apples. You talking about the tools for creating the label beta 4 by 2. Harlan. Standing by to see if he interested response there. How do you ever win for Heartland to chime back in? Heidi? Nope, that was for the fire station. No, I think perhaps it. Didn't put a name until perhaps. This is not a question for you for your patience. I encourage everyone to enter into the stage chat. If you have a specific question to one of our speakers initiated with the name of the speaker so that we know

as we're going through these and we do stay online through the rest of the day. It stays alive that are speaker can go in there and address that question that's addressed to them. That would be fantastic. Give it another half a second and see if anyone enters anything that, I think we may be good. I thank you so much and everyone. I am going to disconnect and reconnect Paul Barbara who is standing by. So give me a minute and my boy to collect his technology. Thank you for Lena's

but tester job.

Cackle comments for the website

Buy this talk

Access to the talk “Voice Assistants in Healthcare”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Ticket

Get access to all videos “MLconf Online 2020”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Ticket

Interested in topic “Artificial Intelligence and Machine Learning”?

You might be interested in videos from this event

February 4 - 5, 2021
Online
26
104
ai, application, bot, chatbot, conversation, data, design, healthcare, ml

Similar talks

Yindalon Aphinyanaphongs
Physician Scientist at NYU Langone Medical Center
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Paul Barba
Chief Scientist at Lexalytics, Inc.
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
John Whaley
Founder at UnifyID
+ 3 speakers
Christoforos Kachris
Founder and CEO at InAccel
+ 3 speakers
Anmol Suag
Data Scientist at Blueshift
+ 3 speakers
Martin Isaksson
CEO at PerceptiLabs
+ 3 speakers
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Buy this video

Video
Access to the talk “Voice Assistants in Healthcare”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Conference Cast

With ConferenceCast.tv, you get access to our library of the world's best conference talks.

Conference Cast
949 conferences
37757 speakers
14408 hours of content