A self-referential childlike model to acquire phones, syllables and words from acoustic speech

Brandl H, Joublin F, Wrede B, Goerick C (2008)
In: 7th IEEE International Conference on Development and Learning. IEEE: 31-36.

Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Konferenzbeitrag | Veröffentlicht | Englisch
Autor
; ; ;
Abstract / Bemerkung
Speech understanding requires the ability to parse spoken utterances into words. But this ability is not innate and needs to be developed by infants within the first years of their life. So far almost all computational speech processing systems neglected this bootstrapping process. Here we propose a model for early infant word learning embedded into a layered architecture comprising phone, phonotactics and syllable learning. Our model uses raw acoustic speech as input and aims to learn the structure of speech unsupervised on different levels of granularity. We present first experiments which evaluate our model on speech corpora that have some of the properties of infant-directed speech. To further motivate our approach we outline how the proposed model integrates into an embodied multi-modal learning and interaction framework running on Honda’s Asimo robot.
Erscheinungsjahr
Titel des Konferenzbandes
7th IEEE International Conference on Development and Learning
Seite
31-36
Konferenz
7th IEEE International Conference on Development and Learning (ICDL 2007)
Konferenzort
Monterey, CA, USA
Konferenzdatum
2008-08-09 – 2008-08-12
PUB-ID

Zitieren

Brandl H, Joublin F, Wrede B, Goerick C. A self-referential childlike model to acquire phones, syllables and words from acoustic speech. In: 7th IEEE International Conference on Development and Learning. IEEE; 2008: 31-36.
Brandl, H., Joublin, F., Wrede, B., & Goerick, C. (2008). A self-referential childlike model to acquire phones, syllables and words from acoustic speech. 7th IEEE International Conference on Development and Learning, 31-36. IEEE. doi:10.1109/DEVLRN.2008.4640801
Brandl, H., Joublin, F., Wrede, B., and Goerick, C. (2008). “A self-referential childlike model to acquire phones, syllables and words from acoustic speech” in 7th IEEE International Conference on Development and Learning (IEEE), 31-36.
Brandl, H., et al., 2008. A self-referential childlike model to acquire phones, syllables and words from acoustic speech. In 7th IEEE International Conference on Development and Learning. IEEE, pp. 31-36.
H. Brandl, et al., “A self-referential childlike model to acquire phones, syllables and words from acoustic speech”, 7th IEEE International Conference on Development and Learning, IEEE, 2008, pp.31-36.
Brandl, H., Joublin, F., Wrede, B., Goerick, C.: A self-referential childlike model to acquire phones, syllables and words from acoustic speech. 7th IEEE International Conference on Development and Learning. p. 31-36. IEEE (2008).
Brandl, Holger, Joublin, Frank, Wrede, Britta, and Goerick, Christian. “A self-referential childlike model to acquire phones, syllables and words from acoustic speech”. 7th IEEE International Conference on Development and Learning. IEEE, 2008. 31-36.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar
ISBN Suche