Automatic Text Clustering for Audio Attribute Elicitation Experiment Responses
×
Cite This
Citation & Abstract
J. Francombe, T. Brookes, and R. Mason, "Automatic Text Clustering for Audio Attribute Elicitation Experiment Responses," Paper 9843, (2017 October.). doi:
J. Francombe, T. Brookes, and R. Mason, "Automatic Text Clustering for Audio Attribute Elicitation Experiment Responses," Paper 9843, (2017 October.). doi:
Abstract: Collection of text data is an integral part of descriptive analysis, a method commonly used in audio quality evaluation experiments. Where large text data sets will be presented to a panel of human assessors (e.g., to group responses that have the same meaning), it is desirable to reduce redundancy as much as possible in advance. Text clustering algorithms have been used to achieve such a reduction. A text clustering algorithm was tested on a dataset for which manual annotation by two experts was also collected. The comparison between the manual annotations and automatically-generated clusters enabled evaluation of the algorithm. While the algorithm could not match human performance, it could produce a similar grouping with a significant redundancy reduction (approximately 48%).
@article{francombe2017automatic,
author={francombe, jon and brookes, tim and mason, russell},
journal={journal of the audio engineering society},
title={automatic text clustering for audio attribute elicitation experiment responses},
year={2017},
volume={},
number={},
pages={},
doi={},
month={october},}
@article{francombe2017automatic,
author={francombe, jon and brookes, tim and mason, russell},
journal={journal of the audio engineering society},
title={automatic text clustering for audio attribute elicitation experiment responses},
year={2017},
volume={},
number={},
pages={},
doi={},
month={october},
abstract={collection of text data is an integral part of descriptive analysis, a method commonly used in audio quality evaluation experiments. where large text data sets will be presented to a panel of human assessors (e.g., to group responses that have the same meaning), it is desirable to reduce redundancy as much as possible in advance. text clustering algorithms have been used to achieve such a reduction. a text clustering algorithm was tested on a dataset for which manual annotation by two experts was also collected. the comparison between the manual annotations and automatically-generated clusters enabled evaluation of the algorithm. while the algorithm could not match human performance, it could produce a similar grouping with a significant redundancy reduction (approximately 48%).},}
TY - paper
TI - Automatic Text Clustering for Audio Attribute Elicitation Experiment Responses
SP -
EP -
AU - Francombe, Jon
AU - Brookes, Tim
AU - Mason, Russell
PY - 2017
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2017
TY - paper
TI - Automatic Text Clustering for Audio Attribute Elicitation Experiment Responses
SP -
EP -
AU - Francombe, Jon
AU - Brookes, Tim
AU - Mason, Russell
PY - 2017
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2017
AB - Collection of text data is an integral part of descriptive analysis, a method commonly used in audio quality evaluation experiments. Where large text data sets will be presented to a panel of human assessors (e.g., to group responses that have the same meaning), it is desirable to reduce redundancy as much as possible in advance. Text clustering algorithms have been used to achieve such a reduction. A text clustering algorithm was tested on a dataset for which manual annotation by two experts was also collected. The comparison between the manual annotations and automatically-generated clusters enabled evaluation of the algorithm. While the algorithm could not match human performance, it could produce a similar grouping with a significant redundancy reduction (approximately 48%).
Collection of text data is an integral part of descriptive analysis, a method commonly used in audio quality evaluation experiments. Where large text data sets will be presented to a panel of human assessors (e.g., to group responses that have the same meaning), it is desirable to reduce redundancy as much as possible in advance. Text clustering algorithms have been used to achieve such a reduction. A text clustering algorithm was tested on a dataset for which manual annotation by two experts was also collected. The comparison between the manual annotations and automatically-generated clusters enabled evaluation of the algorithm. While the algorithm could not match human performance, it could produce a similar grouping with a significant redundancy reduction (approximately 48%).
Authors:
Francombe, Jon; Brookes, Tim; Mason, Russell
Affiliation:
University of Surrey, Guildford, Surrey, UK
AES Convention:
143 (October 2017)
Paper Number:
9843
Publication Date:
October 8, 2017Import into BibTeX
Subject:
Perception—Part 2
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=19240