Presentations (Communicative Events)

Summarizing Speech Without Text Using Hidden Markov Models

Hirschberg, Julia Bell; Maskey, Sameer R.

We present a method for summarizing speech documents without using any type of transcript/text in a Hidden Markov Model framework. The hidden variables or states in the model represent whether a sentence is to be included in a summary or not, and the acoustic/prosodic features are the observation vectors. The model predicts the optimal sequence of segments that best summarize the document. We evaluate our method by comparing the predicted summary with one generated by a human summarizer. Our results indicate that we can generate 'good' summaries even when using only acoustic/prosodic information, which points toward the possibility of text-independent summarization for spoken documents.


  • thumnail for maskey_hirschberg_06b.pdf maskey_hirschberg_06b.pdf application/pdf 47.3 KB Download File

More About This Work

Academic Units
Computer Science
Proceedings of HLT-NAACL
Published Here
July 5, 2013