Print Email Facebook Twitter Personalised models for speech detection from body movements using transductive parameter transfer Title Personalised models for speech detection from body movements using transductive parameter transfer Author Gedik, E. (TU Delft Pattern Recognition and Bioinformatics) Hung, H.S. (TU Delft Pattern Recognition and Bioinformatics) Date 2017-08-01 Abstract We investigate the task of detecting speakers in crowded environments using a single body worn triaxial accelerometer. Detection of such behaviour is very challenging to model as people’s body movements during speech vary greatly. Similar to previous studies, by assuming that body movements are indicative of speech, we show experimentally, on a real-world dataset of 3 h including 18 people, that transductive parameter transfer learning (Zen et al. in Proceedings of the 16th international conference on multimodal interaction. ACM, 2014) can better model individual differences in speaking behaviour, significantly improving on the state-of-the-art performance. We also discuss the challenges introduced by the in-the-wild nature of our dataset and experimentally show how they affect detection performance. We strengthen the need for an adaptive approach by comparing the speech detection problem to a more traditional activity (i.e. walking). We provide an analysis of the transfer by considering different source sets which provides a deeper investigation of the nature of both speech and body movements, in the context of transfer learning. Subject Human behaviourSocial actionsSocial signal processingTransfer learningWearable sensors To reference this document use: http://resolver.tudelft.nl/uuid:4fe22cfc-44da-4f18-ab5b-75a07e14103a DOI https://doi.org/10.1007/s00779-017-1006-4 ISSN 1617-4909 Source Personal and Ubiquitous Computing, 21 (4), 723-737 Part of collection Institutional Repository Document type journal article Rights © 2017 E. Gedik, H.S. Hung Files PDF 10.1007_s00779_017_1006_4.pdf 1.32 MB Close viewer /islandora/object/uuid:4fe22cfc-44da-4f18-ab5b-75a07e14103a/datastream/OBJ/view