Learning to Determine Who is the Better Speaker
- Speech can be more or less likable in various ways and comparing speakers by likability has important applications such as speaker selection or matching. Determining the likability of a speaker is a difficult task which can be simplified by breaking it down into pairwise preference decisions. Using a corpus of 5440 pairwise preference ratings collected previously through crowd-sourcing, we train classifiers to determine which of two speakers is “better”. We find that modeling the speech feature sequences using LSTMs outperforms conventional methods that pre-aggregate feature averages by a large margin, indicating that the prosodic structure should be taken into account when determining speech quality. Our classifier reaches an accuracy of 97 % for coarse-grained decisions, where differences between speech quality in both stimuli is relatively large.
Author: | Timo BaumannORCiDGND |
---|---|
DOI: | https://doi.org/10.21437/SpeechProsody.2018-165 |
Parent Title (English): | Proceedings of the 9th International Conference on Speech Prosody, 13-16 June 2018, Poznań, Poland |
Publisher: | ISCA |
Document Type: | conference proceeding (article) |
Language: | English |
Year of first Publication: | 2018 |
Release Date: | 2022/06/27 |
First Page: | 819 |
Last Page: | 822 |
Institutes: | Fakultät Informatik und Mathematik |
Begutachtungsstatus: | peer-reviewed |
Publication: | Externe Publikationen |
research focus: | Information und Kommunikation |
Licence (German): | Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG |