loading
Documents

Research.Publish.Connect.

Paper

Paper Unlock

Authors: György Szaszák 1 ; Máté Ákos Tündik 1 and András Beke 2

Affiliations: 1 Budapest University of Technology and Economics, Hungary ; 2 Research Institute for Linguistics of the Hungarian Academy of Sciences, Hungary

ISBN: 978-989-758-203-5

Keyword(s): Audio, Speech, Summarization, Tokenization, Speech Recognition, Latent Semantic Indexing.

Related Ontology Subjects/Areas/Topics: Artificial Intelligence ; Computational Intelligence ; Evolutionary Computing ; Information Extraction ; Knowledge Discovery and Information Retrieval ; Knowledge-Based Systems ; Machine Learning ; Pre-Processing and Post-Processing for Data Mining ; Soft Computing ; Symbolic Systems

Abstract: This paper addresses speech summarization of highly spontaneous speech. The audio signal is transcribed using an Automatic Speech Recognizer, which operates at relatively high word error rates due to the complexity of the recognition task and high spontaneity of speech. An analysis is carried out to assess the propagation of speech recognition errors into syntactic parsing. We also propose an automatic, speech prosody based audio tokenization approach and compare it to human performance. The so obtained sentence-like tokens are analysed by the syntactic parser to help ranking based on thematic terms and sentence position. The thematic term is expressed in two ways: TF-IDF and Latent Semantic Indexing. The sentence scores are calculated as a linear combination of the thematic term score and a positional score. The summary is generated from the top 10 candidates. Results show that prosody based tokenization reaches human average performance and that speech recognition errors pr opagate moderately into syntactic parsing (POS tagging and dependency parsing). Nouns prove to be quite error resistant. Audio summarization shows 0.62 recall and 0.79 precision by an F-measure of 0.68, compared to human reference. A subjective test is also carried out on a Likert-scale. All results apply to spontaneous Hungarian. (More)

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.174.43.27

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Szaszák, G.; Tündik, M. and Beke, A. (2016). Summarization of Spontaneous Speech using Automatic Speech Recognition and a Speech Prosody based Tokenizer.In Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2016) ISBN 978-989-758-203-5, pages 221-227. DOI: 10.5220/0006044802210227

@conference{kdir16,
author={György Szaszák. and Máté Ákos Tündik. and András Beke.},
title={Summarization of Spontaneous Speech using Automatic Speech Recognition and a Speech Prosody based Tokenizer},
booktitle={Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2016)},
year={2016},
pages={221-227},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006044802210227},
isbn={978-989-758-203-5},
}

TY - CONF

JO - Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2016)
TI - Summarization of Spontaneous Speech using Automatic Speech Recognition and a Speech Prosody based Tokenizer
SN - 978-989-758-203-5
AU - Szaszák, G.
AU - Tündik, M.
AU - Beke, A.
PY - 2016
SP - 221
EP - 227
DO - 10.5220/0006044802210227

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.