Orbelina Cortez-Barbosa

“Your speech can offer a lot of information and clues into how your brain is functioning,” says Katie Fraser, a PhD candidate in the department of computer science at the University of Toronto.

“Dementia is often linked to language, and using today’s computational tools we can quickly evaluate a person’s speech.”

Dementia is a disease affecting 47.5 million people worldwide (World Health Organization). Research has consistently shown that particular changes in speech and language can signal early onset of the disease.

For Fraser, finding a computational solution for the detection of dementia has been the focus of her research and the idea behind the startup Winterlight Labs Inc.— software that uses natural language processing and machine learning technology to detect signs of dementia using speech samples.

“It’s important to get this research out of the academic sphere and into hands of people who can actually benefit from it,” says Fraser. “I think the best way to do this is to develop a product that people can use.”

Fraser, who specializes in computational linguistics, is supervised by computer science Professor Graeme Hirst and Jed Meltzer, an assistant professor in the department of psychology and a scientist with the Rotman Research Institute at the Baycrest Centre for Geriatric Care.

Several years ago, Hirst, his graduate student Xuan Le, and department of English Professor Ian Lancashire, in consultation with Regina Jokel, assistant professor department of speech-language pathology, used natural language processing techniques to examine the writing of authors Iris Murdoch (who is known to have died of Alzheimer’s), P.D. James (who did not have Alzheimer’s) and Agatha Christie. Hirst says Christie’s writing showed an incredible decline in her vocabulary in her last books, but surprisingly, not in her syntax. They concluded Christie likely died of the disease.

“Our thinking in those days was that what matters is change in a person over time,” says Hirst. “That axiom is not as clear-cut as we thought. Our more recent work is a lot less longitudinal.”

Hirst says that aging inevitably leads to changes in language. Older people do talk more abstractly, and have minor vocabulary-seeking problems. People with dementia rapidly slide down in their vocabulary and noun to verb ratio, and their syntax becomes simpler.

As part of her thesis research, Fraser conducts research on text and speech processing to look for symptoms of dementia. She collects speech samples and analyzes them through speech recognition software and machine learning classifiers. Machine learning classifiers are algorithms that have been trained to classify data into a category or class. In this case the classifiers have been trained to distinguish between a healthy individual and a person with dementia.

Fraser founded Winterlight Labs alongside her colleagues who share similar research interests in computer science and healthcare.

“We had discussed trying to build a company by bringing together all of our expertise.”

The startup was created in the summer of 2015 and includes computer science assistant professor, status-only, Frank Rudzicz, a scientist with the Toronto Rehabilitation Institute – an expert in acoustic processing; Liam Kaufman, whose experience includes Alzheimer’s research, and holds both a degree in computer science and a master’s degree from �Թϱ��’s Institute of Medical Science; and computer science master’s student Maria Yancheva, a computational linguistics student with a background in software engineering and assistive technologies.

Winterlight’s current prototype works by recording a one-to-five-minute speech sample of a person describing an image. The speech sample is then transcribed using automatic speech recognition. Various features of the speech and text sample, including acoustic, lexical, syntactic and semantic aspects are extracted and examined. These features are then put into the machine learning classifier. The prototype has an 81 per cent accuracy rate in classifying speech samples.

In an interview with Faculty of Medicine writer Carolyn Morris, Rudzicz explained how the technology is able to detect cognitive impairment through observations of diction and syntax.

“When it comes to word choice and grammar, for example, one of the signs of cognitive impairment would be the use of simple verbs versus gerunds — so “the kid runs” instead of “there’s a kid running.” People with early signs of dementia will often use pronouns instead of more specific nouns. So “she is washing dishes” instead of “The mother is washing dishes.” Then there’s the interpretation of the images. So, for example, in what we call the “cookie theft” image there’s a woman in a kitchen, an overflowing sink and kids reaching up to steal cookies. Someone with cognitive impairment might notice “a kid on a stool,” but not take that next step to point out that “the son is trying to steal cookies.” Or they’ll comment on the overflowing sink, but not on the woman failing to notice it.”

Game-changing work with the NBA and more from one of world's top ten computer science departments

sgupta — Wed, 15 Apr 2015 11:43:20 +0000

Game-changing work with the NBA and more from one of world's top ten computer science departments sgupta Wed, 04/15/2015 - 07:43

Cutline

Keith Boyarsky, analytics consultant for the Toronto Raptors, who is working with computer science student Jackson Wang on "Neural network for professional basketball" project

Orbelina Cortez-Barbosa

Author legacy

Orbelina Cortez-Barbosa

Topic

Global Lens

Interested in video game design? This is the place to be

sgupta — Thu, 02 Apr 2015 10:21:14 +0000

Interested in video game design? This is the place to be sgupta Thu, 04/02/2015 - 06:21

Cutline

Pitfall Planet (above) is one of 80 games and interactive projects to explore at Level Up (all images courtesy the department of computer science)

Orbelina Cortez-Barbosa

Author legacy

Orbelina Cortez-Barbosa

Topic

City & Culture

Faculty of Arts & Science

Seeking startup ideas at a top-tier computer science department

sgupta — Fri, 06 Mar 2015 09:34:24 +0000

Seeking startup ideas at a top-tier computer science department sgupta Fri, 03/06/2015 - 04:34

Cutline

Members of the department of computer science and ROSS team celebrate at the inaugural Entrepreneurship Day

Orbelina Cortez-Barbosa

Author legacy

Orbelina Cortez-Barbosa

More News

Undergraduate Students

Students

Computer Science

Subheadline

Software‐based incubator set to launch

What happens when one of the world's top ten computer science departments gets involved in entrepreneurship?

University of Toronto students and industry contacts were invited to find out at the department's inaugural Entrepreneurship Day February 27, sponsored by International Business Machines Corporation (IBM).

“Entrepreneurship Day is a new annual event where students can showcase how they are engaging in entrepreneurial activities, whether it be through startups, projects with industry, or their involvement with the programming community,” said Helen Kontozopoulous, coordinator and instructor of entrepreneurship‐related initiatives in the department. “We want to give students a stage where we can highlight the work and inventions they are creating outside of the classroom.”

The department of computer science (DCS) also announced its new Innovation Lab (DCSIL) located within the Gerstein Science Information Centre. The lab joins �Թϱ��'s vast network of entrepreneurship accelerators and incubators. (Read more about �Թϱ��'s Banting & Best Centre for Innovation & Entrepreneurship and �Թϱ��'s ecosystem of programs and courses, mentorship, clubs, and expertise for innovators and researchers developing and growing startups.)

“Our plan is to create an incubator that gives students the chance to use their research and academic skills to create software‐based startups,” said Paul Gries, senior lecturer and associate chair for undergraduate studies in the department.

“The DCS Innovation Lab will introduce students to the structure and dynamics of the software industry and will include students from across the university – from different disciplines – to collaborate with computer science students to create innovative programming ideas.”

Among such multidisciplinary examples is Ross Intelligence, which shared its IBM Watson University Challenge presentation as part of Entrepreneurship Day. The team members spanned the disciplines of computer science, information studies and law and were enrolled in the DCS business of software course that took them to the contest.

They are now a full‐fledged company, part of IBM’s Watson ecosystem. (Read more about the team’s second place finish at the IBM Watson University Challenge.)

“Our students can solve problems through creative and innovative software solutions and computer science is an instrumental core for these multidisciplinary projects,” said Kontozopoulous.

Entrepreneurship Day and initiatives such as the Innovation Lab aim to enhance student’s skills and capitalize on their innovations; this year alone, undergraduate students in computer science have won six medals in cross-Canada and international hackathons.

Upcoming challenges include Aquahacking, presented by the de Gaspé Beaubien Foundation in partnership with IBM, bringing together citizens, field experts and digital professionals who believe technology can serve Québec’s and Canada’s waterways. The first Aquahacking will focus on the Ottawa River.

And for those interested in city building, a city‐wide challenge will create new apps for the City of Toronto.

The department of computer science Innovation Lab will also be offering a summer entrepreneurship program starting this May.

Orbelina Cortez‐Barbosa is a writer with the department of computer science.

picpath

sites/default/files/2015-03-05-entrepreneurship-day.jpg

My Studio Assistant: helping artists share their work with the world

sgupta — Tue, 20 May 2014 09:50:42 +0000

My Studio Assistant: helping artists share their work with the world sgupta Tue, 05/20/2014 - 05:50

Cutline

Startups are all about learning and persistence," says Arsen Tumanyan (photo by Orbelina Cortez-Barbosa)

Orbelina Cortez-Barbosa

Author legacy

Orbelina Cortez-Barbosa

Subheadline

Startup makes it easier for creators to submit, exhibit and sell their art

Sometimes, a little creative collaboration is all it takes to go from concept to startup – especially if the collaborators are a University of Toronto instructor and a graduate student in Computer Science.

“I like the freedom of being creative and building things; that's hard to do when you work for somebody else,” says Arsen Tumanyan, who graduated with his professional master’s degree in computer science last year. “Of course, there are companies that give their employees that freedom, but right now I prefer focusing my energy on building a company rather than joining one.”

Along with former instructor Arnold Wytenburg, Tumanyan is a co-founder of My Studio Assistant, a startup they describe as a user-friendly web publishing solution for visual artists and craft artisans. My Studio Assistant allows artists to create their own websites, upload their art, manage social media, exhibit and sell their art, all using one online platform, says Tumanyan.

And it all began when Tumanyan took Wytenburg’s Business of Software course. Wytenburg had presented the idea for My Studio Assistant as a case study and was so impressed by technical solutions his student proposed for the project, he offered Tumanyan a chance to help him work on his venture.

"We started building Arnold’s product, and for two years we experimented with ideas and prototypes,” Tumanyan remembers. “The product vision grew to a point where it required full-time commitment.”

In October of 2013, he left his job at MoPals as vice-president of mobile applications and shifted his efforts to building and launching My Studio Assistant.

“I was taking a chance leaving my full time job to focus on a bootstrapping startup. However, I also believed I would really regret it if I didn’t take on this challenge.”

Today, Wytenburg is chief executive officer of the startup and Tumanyan is chief technical officer, working on product development, user experience and the technical and design aspects of the platform.

“Before I enrolled in the MScAC program, I only had theoretical knowledge about business, but the program, and courses like CSC454, gave me the opportunity to see that theory in practice and to be part of it,” says Tumanyan. “Startups are all about learning and persistence. And by learning, I mean not only new skills but also learning about your customers’ needs.”

My Studio Assistant is unique, he adds, because it targets a specific niche, offering its clients prepackaged plans customized for the art world. For instance, it has a Gallery & Jury Submission tool, which enables artists to easily put together their applications before submitting their work to an exhibition or a competition.

Tumanyan says there is satisfaction in knowing that by creating an opportunity for himself he is also creating opportunities for others.

“We are offering the latest technological solutions available to artists, and we hope My Studio Assistant is making it easier for them to show their work and share it with the world.”

Orbelina Cortez-Barbosa is a writer with the Department of Computer Science at the University of Toronto.

picpath

sites/default/files/2014-05-16-my-studio-assistant-startup.jpg

Orbelina Cortez-Barbosa

Can natural language processing help detect dementia? This �Թϱ��� grad student is trying to find out

Read more from Rudzicz’s interview with Morris

Game-changing work with the NBA and more from one of world's top ten computer science departments

Interested in video game design? This is the place to be

Seeking startup ideas at a top-tier computer science department

My Studio Assistant: helping artists share their work with the world

Can natural language processing help detect dementia? This �Թϱ�� grad student is trying to find out