Medical transcription is often seen as one of the more mundane tasks that need to be done in the doctor's office. Yet, it's vitally important for making sure that medical records are accurate, and that all of the physician's observations, orders, and conversations with patients is properly documented. Google wanted to see if the voice recognition technologies already available in Google Assistant, Google Home, and Google Translate could be used to automate the transcription process and help doctors, as well as medical scribes, take notes more quickly. In a recent proof of concept study, Google developed a system that utilized two automatic speech recognition models, a Connectionist Temporal Classification (CTC) phoneme-based model and a Listen Attend and Spell (LAS) grapheme-based model, and trained them with over 14,000 hours of recorded speech. The result was a pretty respectable word error rate of 20.1% for the CTC model and 18.9% for the LAS model, although the CTC model required the researchers to clean up noise in the recordings before processing it. Based on the favorable results, Google will be soon start working with physicians and researchers at Stanford University to investigate what types of clinically relevant information can be automatically extracted from medical conversations to reduce the amount time doing documentation and increase productive time with patients.

In the world we live in today, Artificial Intelligence (AI) is everywhere. Some of the places we experience it are very obvious, but sometimes AI is being used in ways we may not even realize. The question we face isn't when AI will begin to play a role in our everyday lives because the answer is that it already is. Rather, we should be asking whether or not we are using it to its full capacity. I had the opportunity to talk to Robert Weideman, Executive Vice President and General Manager of Nuance Enterprise.

Recommender systems take inputs from user history, use an internal ranking algorithm to generate results and possibly optimize this ranking based on feedback. However, often the recommender system is unaware of the actual intent of the user and simply provides recommendations dynamically without properly understanding the thought process of the user. An intelligent recommender system is not only useful for the user but also for businesses which want to learn the tendencies of their users. Finding out tendencies or intents of a user is a difficult problem to solve. Keeping this in mind, we sought out to create an intelligent system which will keep track of the user's activity on a web-application as well as determine the intent of the user in each session. We devised a way to encode the user's activity through the sessions. Then, we have represented the information seen by the user in a high dimensional format which is reduced to lower dimensions using tensor factorization techniques. The aspect of intent awareness (or scoring) is dealt with at this stage. Finally, combining the user activity data with the contextual information gives the recommendation score. The final recommendations are then ranked using filtering and collaborative recommendation techniques to show the top-k recommendations to the user. A provision for feedback is also envisioned in the current system which informs the model to update the various weights in the recommender system. Our overall model aims to combine both frequency-based and context-based recommendation systems and quantify the intent of a user to provide better recommendations. We ran experiments on real-world timestamped user activity data, in the setting of recommending reports to the users of a business analytics tool and the results are better than the baselines. We also tuned certain aspects of our model to arrive at optimized results.

Learning distributed representations of documents has pushed the state-of-the-art in several natural language processing tasks and was successfully applied to the field of recommender systems recently. In this paper, we propose a novel content-based recommender system based on learned representations and a generative model of user interest. Our method works as follows: First, we learn representations on a corpus of text documents. Then, we capture a user's interest as a generative model in the space of the document representations. In particular, we model the distribution of interest for each user as a Gaussian mixture model (GMM). Recommendations can be obtained directly by sampling from a user's generative model. Using Latent semantic analysis (LSA) as comparison, we compute and explore document representations on the Delicious bookmarks dataset, a standard benchmark for recommender systems. We then perform density estimation in both spaces and show that learned representations outperform LSA in terms of predictive performance.

The global recorded music market grew by 5.9 percent last year. It was the fastest rate of growth since 1997 and was as a result of the shift from traditional CDs and portable devices to the ability to stream content anywhere, at any time. Yet despite an estimated 498 online music streaming services available in over 40 countries in 2007, many of these companies cease to exist today. This emphasizes the importance of building a clear growth strategy that can continuously appeal to a demographic that is yearning for instant and tailored music on demand. Today, brands across the globe are continually searching for fresh ways to connect and resonate with their audiences while striving to stand out from the competition in order to grow their business.

Your message has been sent. There was an error emailing this page. From smart light bulbs and thermostats that think for themselves to Bluetooth door locks, wireless security cameras, and all manner of sensors, today's home technology can sound awfully sophisticated while actually being a messy hodgepodge of gizmos and apps. Whether you call it home automation or the connected home, installing all this stuff in your house is one thing. Getting it to work together smoothly and with a single user interface can be something entirely different.

Maybe there's an audiophile on your list, or maybe you're shopping for someone who recently acquired a new phone and could use something better than the pack-in headphones. Either way, we have a slew of recommendations in the audio gear section of our holiday gift guide. On our list you'll find smart speakers from Google and Amazon alike, along with Sonos, whose new "One" speaker includes Alexa built in, with Google Assistant support coming soon. When it comes to headphones, our selections run the gamut from the affordable (Jabra's Move headset) to the high end (Bragi's Dash Pro wireless earbuds and these noise cancelling headphones from Sony), with a couple mid-range options in between. Rounding out the list, we have a soundbar, drum machine, synth app, the Amazon Echo Show and one of our favorite portable Bluetooth speakers.

"Right now, you definitely don't need one," said David Pierce, a senior writer at Wired who has reviewed both the Google Home Mini and Amazon Echo Show. "But you should get one! Once you get used to all the small things they can do, like play music or tell you the weather or convert tablespoons to cups while you're mid-recipe, it's hard to go back ... They're playthings. And truly, neither Amazon nor Google's gadget is "better," according to our experts, though one might be a better fit for a given user. "Both speakers perform different tasks really well and really poorly," said Alex Hernandez, editor-in-chief of tech site Techaeris. "It will come down to what you want to do with your smart speaker." The Echo "can control a wider range of smart home devices" than Google Home, said Alex Cranz, senior reviews editor at Gizmodo. That is, of course, if you have smart home devices to control. Our experts agree that Google Home's main draw is its ability to answer complex questions like "What were last week's lottery numbers?" Google Home is "supremely smart thanks to Google's dominance in search," said Nick Pino, a senior editor at TechRadar. "It can tell you things like how much airplane tickets cost, or when movies, games or music originally came out ... Alexa pretty frequently doesn't know how to answer your questions." Plus, they say Google Home is better at understanding your voice. With Echo, "you have to be very specific in how you word your requests, and they can often come out sounding like word salad.

If you buy a new Nissan, you can tell Amazon's Alexa to unlock the car before you leave the house. If you buy a new Ford, you sit behind the wheel and tell Alexa to order diapers or ask about the weather. But those capabilities are trivial compared with the kind of power that a true virtual personal assistant would have to understand your commands and improve the driving experience. Wouldn't it be great to get into the car and just tell it what you want, without worrying about apps and devices and what's incompatible with what? How much washer fluid do I have left?

Artificial Intelligence (AI) has gained worldwide exposure over the years through Hollywood, including the recent blockbuster movies such as Alien: Covenant and Blade Runner 2049. While androids like those depicted in the movies are nothing but science fiction at this point in time, we are seeing the increasingly advanced application of AI incorporate mainstream computing. In this post, we examine how website development is benefiting from artificial intelligence (AI), as well as some unique integration challenges. Modern mainstream website development has focused on the building of a customer-facing front-end presence on the Internet and the integration of the front-end with enterprise back-office operations. Drupal is an industry-leading open-sourced platform for building such enterprise websites.