Using Audio Transformations to Improve Comprehension in Voice Question Answering

Chuklin, A, Severyn, A, Trippas, J, Alfonseca, E, Silen, H and Spina, D 2019, 'Using Audio Transformations to Improve Comprehension in Voice Question Answering', in F. Crestani et al. (ed.) Experimental IR Meets Multilinguality, Multimodality, and Interaction, Lugano, Switzerland, 9-12 September 2019, pp. 164-170.


Document type: Conference Paper
Collection: Conference Papers

Title Using Audio Transformations to Improve Comprehension in Voice Question Answering
Author(s) Chuklin, A
Severyn, A
Trippas, J
Alfonseca, E
Silen, H
Spina, D
Year 2019
Conference name Conference and Labs of the Evaluation Forum 2
Conference location Lugano, Switzerland
Conference dates 9-12 September 2019
Proceedings title Experimental IR Meets Multilinguality, Multimodality, and Interaction
Editor(s) F. Crestani et al.
Publisher Springer
Place of publication Cham, Swtizerland
Start page 164
End page 170
Total pages 7
Abstract Many popular form factors of digital assistantssuch as Amazon Echo or Google Homeenable users to converse with speech-based systems. The lack of screens presents unique challenges. To satisfy users information needs, the presentation of answers has to be optimized for voice-only interactions. We evaluate the usefulness of audio transformations (i.e., prosodic modifications) for voice-only question answering. We introduce a crowdsourcing setup evaluating the quality of our proposed modifications along multiple dimensions corresponding to the informativeness, naturalness, and ability of users to identify key parts of the answer. We offer a set of prosodic modifications that highlight potentially important parts of the answer using various acoustic cues. Our experiments show that different modifications lead to better comprehension at the expense of slightly degraded naturalness of the audio.
Subjects Information Retrieval and Web Search
Coding and Information Theory
Keyword(s) Speech generation
Question answering
Crowdsourcing
DOI - identifier 10.1007/978-3-030-28577-7_12
Copyright notice © Springer Nature Switzerland AG 2019
ISBN 9783030285760
Versions
Version Filter Type
Altmetric details:
Access Statistics: 10 Abstract Views  -  Detailed Statistics
Created: Wed, 23 Oct 2019, 08:59:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us