Using Imitation to learn Infant-Adult Acoustic Mappings
2011 (English)In: 12th Annual Conference Of The International Speech Communication Association 2011 (INTERSPEECH 2011), Vols 1-5, ISCA , 2011, 772-775 p.Conference paper (Refereed)
This paper discusses a model which conceptually demonstrates how infants could learn the normalization between infant-adult acoustics. The model proposes that the mapping can be inferred from the topological correspondences between the adult and infant acoustic spaces, that are clustered separately in an unsupervised manner. The model requires feedback from the adult in order to select the right topology for clustering, which is a crucial aspect of the model. The feedback Is in terms of an overall rating of the imitation effort by the infant, rather than a frame-by-frame correspondence. Using synthetic, but continuous speech data, we demonstrate that clusters, which have a good topological correspondence, are perceived to be similar by a phonetically trained listener.
Place, publisher, year, edition, pages
ISCA , 2011. 772-775 p.
, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, ISSN 1990-9772 ; 2011
infant speech acquisition, unsupervised learning, self organizing maps
Computer Science Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:kth:diva-52239ISI: 000316502200195ScopusID: 2-s2.0-84865803831ISBN: 978-1-61839-270-1OAI: oai:DiVA.org:kth-52239DiVA: diva2:465535
12th Annual Conference of the International Speech Communication Association, Florence, Italy, 28-31 August 2011
QC 201112202011-12-142011-12-142013-12-13Bibliographically approved