Change search
ReferencesLink to record
Permanent link

Direct link
Biologically Inspired Methods for Automatic Speech Understanding
KTH, School of Computer Science and Communication (CSC), Speech, Music and Hearing, TMH, Speech Communication and Technology.ORCID iD: 0000-0002-3323-5311
2013 (English)In: Biologically Inspired Cognitive Architectures 2012 / [ed] Chella, A; Pirrone, R; Sorbello, R; Johannsdottir, KR, Springer, 2013, Vol. 196, 283-286 p.Conference paper (Refereed)
Abstract [en]

Automatic Speech Recognition (ASR) and Understanding (ASU) systems heavily rely on machine learning techniques to solve the problem of mapping spoken utterances into words and meanings. The statistical methods employed, however, greatly deviate from the processes involved in human language acquisition in a number of key aspects. Although ASR and ASU have recently reached a level of accuracy that is sufficient for some practical applications, there are still severe limitations due, for example, to the amount of training data required and the lack of generalization of the resulting models. In our opinion, there is a need for a paradigm shift and speech technology should address some of the challenges that humans face when learning a first language and that are currently ignored by the ASR and ASU methods. In this paper, we point out some of the aspects that could lead to more robust and flexible models, and we describe some of the research we and other researchers have performed in the area.

Place, publisher, year, edition, pages
Springer, 2013. Vol. 196, 283-286 p.
, Advances in Intelligent Systems and Computing, ISSN 2194-5357 ; 196
Keyword [en]
embodied cognition, grounding meaning, language acquisition, speech technology, unsupervised learning, voice mapping
National Category
Computer Science Language Technology (Computational Linguistics)
URN: urn:nbn:se:kth:diva-109387DOI: 10.1007/978-3-642-34274-5_49ISI: 000313923100049ScopusID: 2-s2.0-84870809865ISBN: 978-364234273-8OAI: diva2:581726
5th Annual International Conference on Biologically Inspired Cognitive Architectures, BICA 2012; Palermo;31 October 2012 through 3 November 2012

QC 20130205

Available from: 2013-01-02 Created: 2013-01-02 Last updated: 2013-03-08Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Salvi, Giampiero
By organisation
Speech Communication and Technology
Computer ScienceLanguage Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 55 hits
ReferencesLink to record
Permanent link

Direct link