Year: 2018
Type: preprint
Abstract: In this paper we introduce a novel pattern match neural network architecture that uses neighbor similarity scores as features, eliminating the need for feature engineering in a disfluency detection task. We evaluate the approach in disfluency detection for four different speech genres, showing that the approach is as effective as hand-engineered pattern match features when used on in-domain data and achieves superior performance in cross-domain scenarios.
Source: arXiv (Cornell University)
Authors: Zayats, Vicky, Ostendorf, Mari
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2901791227