Comparison of syllabification algorithms and training strategies for robust word count estimation across different languages and recording conditions
Loading...
Access rights
openAccess
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A4 Artikkeli konferenssijulkaisussa
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
2018-01-01
Major/Subject
Mcode
Degree programme
Language
en
Pages
5
Series
Proceedings of Interspeech, Volume 2018-September, pp. 1200-1204, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Abstract
Word count estimation (WCE) from audio recordings has a number of applications, including quantifying the amount of speech that language-learning infants hear in their natural environments, as captured by daylong recordings made with devices worn by infants. To be applicable in a wide range of scenarios and also low-resource domains, WCE tools should be extremely robust against varying signal conditions and require minimal access to labeled training data in the target domain. For this purpose, earlier work has used automatic syllabification of speech, followed by a least-squares-mapping of syllables to word counts. This paper compares a number of previously proposed syllabifiers in the WCE task, including a supervised bi-directional long short-term memory (BLSTM) network that is trained on a language for which high quality syllable annotations are available (a “high resource language”), and reports how the alternative methods compare on different languages and signal conditions. We also explore additive noise and varying-channel data augmentation strategies for BLSTM training, and show how they improve performance in both matching and mismatching languages. Intriguingly, we also find that even though the BLSTM works on languages beyond its training data, the unsupervised algorithms can still outperform it in challenging signal conditions on novel languages.Description
Keywords
Daylong recordings, Language acquisition, Noise robustness, Syllabification, Word count estimation
Other note
Citation
Räsänen, O, Seshadri, S & Casillas, M 2018, Comparison of syllabification algorithms and training strategies for robust word count estimation across different languages and recording conditions . in Proceedings of Interspeech . vol. 2018-September, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech Communication Association (ISCA), pp. 1200-1204, Interspeech, Hyderabad, India, 02/09/2018 . https://doi.org/10.21437/Interspeech.2018-1047