8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Web-Based Language Modelling for Automatic Lecture Transcription

Cosmin Munteanu, Gerald Penn, Ron Baecker

University of Toronto, Canada

Universities have long relied on written text to share knowledge. As more lectures are made available on-line, these must be accompanied by textual transcripts in order to provide the same access to information as textbooks. While Automatic Speech Recognition (ASR) is a cost-effective method to deliver transcriptions, its accuracy for lectures is not yet satisfactory. One approach for improving lecture ASR is to build smaller, topic-dependent Language Models (LMs) and combine them (through LM interpolation or hypothesis space combination) with general-purpose, large-vocabulary LMs. In this paper, we propose a simple solution for lecture ASR with similar or better Word Error Rate reductions (as well as topic-specific keyword identification accuracies) than combination-based approaches. Our method eliminates the need for two types of LMs by exploiting the lecture slides to collect a web corpus appropriate for modelling both the conversational and the topic-specific styles of lectures.

Full Paper

Bibliographic reference.  Munteanu, Cosmin / Penn, Gerald / Baecker, Ron (2007): "Web-based language modelling for automatic lecture transcription", In INTERSPEECH-2007, 2353-2356.