Work

Minimum cut model for spoken lecture segmentation

Year: 2006

Type: conference-paper

Abstract: We consider the task of unsupervised lecture segmentation. We formalize segmentation as a graph-partitioning task that optimizes the normalized cut criterion. Our approach moves beyond localized comparisons and takes into account long-range cohesion dependencies. Our results demonstrate that global analysis improves the segmentation accuracy and is robust in the presence of speech recognition errors.

DOI: 10.3115/1220175.1220179

Authors: Igor Malioutov, Regina Barzilay

Institution: Massachusetts Institute of Technology

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funder: National Science Foundation

Awards: Automatic Processing of Spoken and Written Lecture Material, G6671297155, CAREER: Content and Cohesion Models, with Applications to Text Summarization and Natural Language Generation

OpenAlex ID: W2118612506

FWCI: 9.605

Cites: 38

Cited by: 208

Related to: 10