Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2016 Jan 2;31(1):4-18.
doi: 10.1080/23273798.2015.1081703. Epub 2015 Sep 4.

Prediction, Bayesian inference and feedback in speech recognition

Dennis Norris  1 , James M McQueen  2 , Anne Cutler  3
Affiliations

Prediction, Bayesian inference and feedback in speech recognition

Dennis Norris et al. Lang Cogn Neurosci. .

Abstract

Speech perception involves prediction, but how is that prediction implemented? In cognitive models prediction has often been taken to imply that there is feedback of activation from lexical to pre-lexical processes as implemented in interactive-activation models (IAMs). We show that simple activation feedback does not actually improve speech recognition. However, other forms of feedback can be beneficial. In particular, feedback can enable the listener to adapt to changing input, and can potentially help the listener to recognise unusual input, or recognise speech in the presence of competing sounds. The common feature of these helpful forms of feedback is that they are all ways of optimising the performance of speech recognition using Bayesian inference. That is, listeners make predictions about speech because speech recognition is optimal in the sense captured in Bayesian models.

Keywords: Bayesian inference; Speech recognition; feedback; prediction.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.
Connectionist network given the sequence /haıdıər/.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Abdel-Hamid O., Deng L., Yu D. 2013 Exploring convolutional neural network structures and optimization techniques for speech recognition. Proceedings of Interspeech 2013, Lyon (pp. 3366–3370)
    1. Altmann G. T. M., Kamide Y. Incremental interpretation at verbs: Restricting the domain of subsequent reference. Cognition. 1999:247–264. doi: 10.1016/S0010-0277(99)00059-1. - DOI - PubMed
    1. Arai M., Keller F. The use of verb-specific information for prediction in sentence processing. Language and Cognitive Processes. 2013:525–560. doi: 10.1080/01690965.2012.658072. - DOI
    1. Bever T. G., Poeppel D. Analysis by synthesis: A (re-)emerging program of research for language and vision. Biolinguistics. 2010:174–200. ISSN 1450–3417.
    1. Brouwer S., Mitterer H., Huettig F. Discourse context and the recognition of reduced and canonical spoken words. Applied Psycholinguistics. 2013:519–539. doi: 10.1017/S0142716411000853. - DOI