LM10-challenge

LM10-challenge - Language Modelling Challenge Goal to...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
1 6.345/HST.728 Automatic Speech Recognition (2010) LM Challenge 1 Language Modelling Challenge Goal: to create a low perplexity language model that can be used to improve the automatic transcription of lectures Resources: – A corpus of ~240 hours of transcribed lecture material from MIT subjects (e.g., Algebra, Physics etc.), and ~100 MIT World seminars – A companion textbook to the computer science class – Switchboard human-human transcripts – A common 49K word vocabulary – Anything else you want to explore… 1) I've been talking -- I've been multiplying matrices already, but certainly time for me to discuss the rules for matrix multiplication. 2) And the interesting part is the many ways you can do it, and they all give the same answer. 3) So it's -- and they're all important. 4) So matrix multiplication, and then, uh, come inverses. 5) So we're -- uh, we -- mentioned the inverse of a matrix, but there's -- that's a big deal. 6)
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 3

LM10-challenge - Language Modelling Challenge Goal to...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online