Automatic Paragraph Segmentation with Lexical and Prosodic Features

Catherine Lai, Mireia Farrús, Johanna Moore

Research output: Chapter in Book/Report/Conference proceedingConference contribution


As long-form spoken documents become more ubiquitous in everyday life, so does the need for automatic discourse segmentation in spoken language processing tasks. Although previous work has focused on broad topic segmentation, detection of finer-grained discourse units, such as paragraphs, is highly desirable for presenting and analyzing spoken content. To better understand how different aspects of speech cue these subtle discourse transitions, we investigate automatic paragraph segmentation of TED talks. We build lexical and prosodic paragraph segmenters using Support Vector Machines, AdaBoost, and Long Short Term Memory (LSTM) recurrent neural networks. In general, we find that induced cue words and supra-sentential prosodic features outperform features based on topical coherence, syntactic form and complexity. However, our best performance is achieved by combining a wide range of individually weak lexical and prosodic features, with the sequence modelling LSTM generally outperforming the other classifiers by a large margin. Moreover, we find that models that allow lower level interactions between different feature types produce better results than treating lexical and prosodic contributions as separate, independent information sources.
Original languageEnglish
Title of host publicationInterspeech 2016
Place of PublicationSan Francisco, United States
Number of pages5
Publication statusPublished - 12 Sep 2016
EventInterspeech 2016 - San Francisco, United States
Duration: 8 Sep 201612 Sep 2016

Publication series

PublisherInternational Speech Communication Association
ISSN (Electronic)1990-9772


ConferenceInterspeech 2016
CountryUnited States
CitySan Francisco
Internet address


  • prosody
  • discourse
  • segmentation
  • paragraph
  • coherence


Dive into the research topics of 'Automatic Paragraph Segmentation with Lexical and Prosodic Features'. Together they form a unique fingerprint.

Cite this