{"id":8135,"date":"2016-03-25T05:38:49","date_gmt":"2016-03-25T05:38:49","guid":{"rendered":"http:\/\/revoscience.com\/en\/?p=8135"},"modified":"2016-03-25T05:38:49","modified_gmt":"2016-03-25T05:38:49","slug":"voice-controlled-calorie-counter","status":"publish","type":"post","link":"https:\/\/www.revoscience.com\/en\/voice-controlled-calorie-counter\/","title":{"rendered":"Voice-controlled calorie counter"},"content":{"rendered":"

Spoken-language app makes meal logging easier, could aid weight loss.<\/strong><\/em><\/span><\/p>\n

\"A<\/a>
A prototype of a new speech-controlled nutrition-logging system allows users to verbally describe the contents of a meal. The system then parses the description and automatically retrieves the pertinent nutritional data.
Illustration: Jose-Luis Olivares\/MIT<\/figcaption><\/figure>\n

CAMBRIDGE, Mass.<\/strong> —\u00a0For people struggling with obesity, logging calorie counts and other nutritional information at every meal is a proven way to lose weight. The technique does require consistency and accuracy, however, and when it fails, it\u2019s usually because people don’t have the time to find and record all the information they need.<\/span><\/p>\n

A few years ago, a team of nutritionists from Tufts University who had been experimenting with mobile-phone apps for recording caloric intake approached members of the Spoken Language Systems Group at MIT\u2019s Computer Science and Artificial Intelligence Laboratory (CSAIL), with the idea of a spoken-language application that would make meal logging even easier.<\/span><\/p>\n

This week, at the International Conference on Acoustics, Speech, and Signal Processing in Shanghai, the MIT researchers are presenting a Web-based prototype of their speech-controlled nutrition-logging system.<\/span><\/p>\n

With it, the user verbally describes the contents of a meal, and the system parses the description and automatically retrieves the pertinent nutritional data from an online database maintained by the U.S. Department of Agriculture (USDA).<\/span><\/p>\n

[pullquote]The researchers report the results of experiments with a speech-recognition system that they developed specifically to handle food-related terminology.[\/pullquote]<\/p>\n

The data is displayed together with images of the corresponding foods and pull-down menus that allow the user to refine their descriptions \u2014 selecting, for instance, precise quantities of food. But those refinements can also be made verbally. A user who begins by saying, \u201cFor breakfast, I had a bowl of oatmeal, bananas, and a glass of orange juice\u201d can then make the amendment, \u201cI had half a banana,\u201d and the system will update the data it displays about bananas while leaving the rest unchanged.<\/span><\/p>\n

\u201cWhat [the Tufts nutritionists] have experienced is that the apps that were out there to help people try to log meals tended to be a little tedious, and therefore people didn\u2019t keep up with them,\u201d says James Glass, a senior research scientist at CSAIL, who leads the Spoken Language Systems Group. \u201cSo they were looking for ways that were accurate and easy to input information.\u201d<\/span><\/p>\n

The first author on the new paper is Mandy Korpusik, an MIT graduate student in electrical engineering and computer science. She\u2019s joined by Glass, who\u2019s her thesis advisor; her fellow graduate student Michael Price; and by Calvin Huang, an undergraduate researcher in Glass\u2019s group.<\/span><\/p>\n

Context sensitivity<\/strong><\/span><\/p>\n

In the paper, the researchers report the results of experiments with a speech-recognition system that they developed specifically to handle food-related terminology. But that wasn\u2019t the main focus of their work; indeed, an online demo of their meal-logging system instead uses Google\u2019s free speech-recognition app.<\/span><\/p>\n

Their research concentrated on two other problems. One is identifying words\u2019 functional role: The system needs to recognize that if the user records the phrase \u201cbowl of oatmeal,\u201d nutritional information on oatmeal is pertinent, but if the phrase is \u201coatmeal cookie,\u201d it\u2019s not.<\/span><\/p>\n

The other problem is reconciling the user\u2019s phrasing with the entries in the USDA database. For instance, the USDA data on oatmeal is recorded under the heading \u201coats\u201d; the word \u201coatmeal\u201d shows up nowhere in the entry.<\/span><\/p>\n

To address the first problem, the researchers used machine learning. Through the Amazon Mechanical Turk crowdsourcing platform, they recruited workers who simply described what they\u2019d eaten at recent meals, then labeled the pertinent words in the description as names of foods, quantities, brand names, or modifiers of the food names. In \u201cbowl of oatmeal,\u201d \u201cbowl\u201d is a quantity and \u201coatmeal\u201d is a food, but in \u201coatmeal cookie,\u201d oatmeal is a modifier.<\/span><\/p>\n

Once they had roughly 10,000 labeled meal descriptions, the researchers used machine-learning algorithms to find patterns in the syntactic relationships between words that would identify their functional roles.<\/span><\/p>\n

Semantic matching<\/strong><\/span><\/p>\n

To translate between users\u2019 descriptions and the labels in the USDA database, the researchers used an open-source database called Freebase, which has entries on more than 8,000 common food items, many of which include synonyms. Where synonyms were lacking, they again recruited Mechanical Turk workers to supply them.<\/span><\/p>\n

The version of the system presented at the conference is intended chiefly to demonstrate the viability of its approach to natural-language processing; it reports calorie counts but doesn\u2019t yet total them automatically. A version that does is in the works, however, and when it\u2019s complete, the Tufts researchers plan to conduct a user study to determine whether it indeed makes nutrition logging easier.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

This week, at the International Conference on Acoustics, Speech, and Signal Processing in Shanghai, the MIT researchers are presenting a Web-based prototype of their speech-controlled nutrition-logging system.<\/p>\n","protected":false},"author":6,"featured_media":8136,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[24,17,28],"tags":[],"class_list":["post-8135","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-fitness","category-research","category-techbiz"],"featured_image_urls":{"full":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",639,426,false],"thumbnail":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0-150x150.jpg",150,150,true],"medium":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0-300x200.jpg",300,200,true],"medium_large":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",639,426,false],"large":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",639,426,false],"1536x1536":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",639,426,false],"2048x2048":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",639,426,false],"ultp_layout_landscape_large":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",639,426,false],"ultp_layout_landscape":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",639,426,false],"ultp_layout_portrait":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",600,400,false],"ultp_layout_square":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",600,400,false],"newspaper-x-single-post":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",639,426,false],"newspaper-x-recent-post-big":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",540,360,false],"newspaper-x-recent-post-list-image":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",95,63,false],"web-stories-poster-portrait":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",639,426,false],"web-stories-publisher-logo":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",96,64,false],"web-stories-thumbnail":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2016\/03\/MIT-Nutrition-Log_0.jpg",150,100,false]},"author_info":{"info":["Amrita Tuladhar"]},"category_info":"Fitness<\/a> Research<\/a> Tech<\/a>","tag_info":"Tech","comment_count":"0","_links":{"self":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/posts\/8135","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/comments?post=8135"}],"version-history":[{"count":0,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/posts\/8135\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/media\/8136"}],"wp:attachment":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/media?parent=8135"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/categories?post=8135"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/tags?post=8135"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}