Search
 
loader loading subjects...
cover
Bidirectional LSTM for Automatic Punctuation Restoration
Askars Salimbajevs
59 - 65
10.3233/978-1-61499-701-6-59
Frontiers in Artificial Intelligence and Applications
Volume 289: Human Language Technologies – The Baltic Perspective
Abstract

The output of generic automatic speech recognition systems consists of raw word sequences without any punctuation symbols. When sequences are longer, it is difficult for humans to read and understand them. Also, many natural language understanding and processing tools expect that input will contain punctuation. We present a bidirectional recurrent neural network for punctuation restoration in speech utterances. The proposed model showed promising results, F1-scores of 0.732 for commas and 0.708 for periods on raw output from a speech recognizer.

Download
Creative Commons License