This site has been archived

Archives for August 2010

Customizing the Google Search Appliance for Greenfield OCW

MIT’s OpenCourseWare uses MIT’s Google Search Appliance (GSA) to search its content.  MIT supports customization of GSA results through XSL transformation.  This post describes how we plan to use GSA to search lecture transcripts and return results containing the lecture videos that the search terms appear in.  Since OCW publishes static content, it doesn’t incorporate an integral search engine.  Search is provided through Continue Reading

How Google Translate Works

Google posted a high level overview of how Google Translate works.

Source: Google

Running the Baseline Recognizer

The software that processes lecture audio into a textual transcript is comprised of a series of scripts that marshall input files and parameters to a speech recognition engine.  Interestingly, since the engine is data driven, its code seldom changes; improvements in performance and accuracy are achieved by refining the data it uses to perform its tasks.

There are two steps to produce the transcript.  The first creates an audio file in the correct format for speech recognition.  The second processes that audio file into the transcript.

Continue Reading

Creative Commons License Unless otherwise specified, the Spoken Media Website by the MIT Office of Digital Learning, Strategic Education Initiatives is licensed under a Creative Commons Attribution 4.0 International License.