How to Wreck a Nice Beach, You Sing Calm Incense: An Introduction to Computer Speech Recognition

Sunday, February 14th, 3:00 pm

Location: meet up in tearoom, move to Ryerson

Lecture by Sam Bowman


Computer speech recognition has been a focus of research since well before the invention of the modern computer, and in the last twenty years it has gotten to the point that given some constraints, it can be as accurate as a human transcriber. However, the holy grail of speaker-independent, large vocabulary recognition is still slightly out of reach.

I’ll give a very, very brief history of the development of the models that came into the mainstream in the 1990s, and then try to give a relatively math-light description of how these models work, and how people here and elsewhere are working to improve them.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: