Google Research

Restoring Punctuation and Capitalization in Transcribed Speech

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2009), pp. 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.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work