Restoring punctuation and capitalization in transcribed speech
Authors:
- 1 April 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 4741-4744
Abstract
Adding punctuation and capitalization greatly improves the readability of automatic speech transcripts. We discuss an approach for performing both tasks in a single pass using a purely text-based n-gram language model. We study the effect on performance of varying the n-gram order (from n = 3 to n = 6) and the amount of training data (from 58 million to 55 billion tokens). Our results show that using larger training data sets consistently improves performance, while increasing the n-gram order does not help nearly as much.Keywords
This publication has 7 references indexed in Scilit:
- Punctuating speech for information extractionInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008
- Adaptation of maximum entropy capitalizer: Little data can help a lotComputer Speech & Language, 2006
- Enriching speech recognition with automatic detection of sentence boundaries and disfluenciesIEEE Transactions on Audio, Speech, and Language Processing, 2006
- Capitalizing machine translation2006
- Cyberpunc: a lightweight punctuation annotation system for speech2002
- Capitalization Recovery for TextLecture Notes in Computer Science, 2002
- Prosody-based automatic segmentation of speech into sentences and topicsSpeech Communication, 2000