Header

UZH-Logo

Maintenance Infos

Speaker-independent isolated digit recognition using an AER silicon cochlea


Abdollahi, M; Liu, S-C (2011). Speaker-independent isolated digit recognition using an AER silicon cochlea. In: IEEE Biomedical Circuits and Systems Conference (BioCAS) 2011, San Diego, USA, 10 November 2011 - 12 November 2011, 269-272.

Abstract

This paper presents speaker-independent isolated digit recognition experiments based on cochlear image maps that were computed using spatio-temporal spike patterns obtained from an Address-Event Representation silicon cochlea. The cochlear maps used in this study were computed by means of: (i) time-binned spike-counts; (ii) low-pass filtered spike trains; and (iii) Radon spike-count method. These maps were subsequently used as input to a back-end classifier of Support Vector Machines. The results show promising recognition accuracies on near 110 speakers from the TIDIGITS database. In fact, it is shown that despite the limited input dynamic range and the un-modelled nonlinearities produced by the hardware cochlea, the discriminative information present in its spike patterns can potentially be sufficient for a task as complex as speaker-independent isolated keyword recognition. Results report over 95% average word recognition accuracy on utterances by an unseen set of speakers.

Abstract

This paper presents speaker-independent isolated digit recognition experiments based on cochlear image maps that were computed using spatio-temporal spike patterns obtained from an Address-Event Representation silicon cochlea. The cochlear maps used in this study were computed by means of: (i) time-binned spike-counts; (ii) low-pass filtered spike trains; and (iii) Radon spike-count method. These maps were subsequently used as input to a back-end classifier of Support Vector Machines. The results show promising recognition accuracies on near 110 speakers from the TIDIGITS database. In fact, it is shown that despite the limited input dynamic range and the un-modelled nonlinearities produced by the hardware cochlea, the discriminative information present in its spike patterns can potentially be sufficient for a task as complex as speaker-independent isolated keyword recognition. Results report over 95% average word recognition accuracy on utterances by an unseen set of speakers.

Statistics

Altmetrics

Additional indexing

Item Type:Conference or Workshop Item (Speech), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Event End Date:12 November 2011
Deposited On:03 Sep 2014 13:07
Last Modified:12 Aug 2017 14:39
Publisher:Proceedings of IEEE Biomedical Circuits and Systems Conference (BioCAS), 2011
Series Name:IEEE Biomedical Circuits and Systems Conference
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1109/BioCAS.2011.6107779

Download

Full text not available from this repository.
View at publisher