Abstract
In this paper we present IBM Embedded ViaVoice (EVV), a speech recognizer for embedded devices. It is designed for grammar-based command and control applications with medium to large vocabularies. We show what algorithms and technologies were used to cope with the fundamental problems of embedded systems: limited CPU performance, slow memory, no floating point unit, and the division of the memory into ROM and RAM. The scalable EVV system described is capable of real-time performance on embedded platforms as slow as 40 MIPS with minimal RAM around 1 MB.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Deligne, S., Eide, E., Gopinath, R.A., Kanevksy, D., Maison, B., Olsen, P., Printz, H., Šedivý, J.: Low-Resource Speech Recognition of 500-word Vocabularies In: EuroSpeech 2001, Proceedings (2001)
Balakrishnan, S.V.: Fast Incremental Adaptation using Maximum Likelihood Regression and Stochastic Gradient Descent. In: EuroSpeech 2003, Proceedings (8th European Conference on Speech Communication and Technology) (2003)
Novák, M., Gopinath, R.A., Šedivý, J.: Efficient Hierarchical Labeler Algorithm for Gaussian Likelihoods Computation in Resource Constrained Speech Recognition Systems, http://www.research.ibm.com/people/r/rameshg/novak-icassp2002.ps
Bahl, L.R., de Souza, P.V., Gopalakrishnan, P.S., Nahamoo, D., Picheny, M.A.: Robust methods for using context-dependent features and speech recognition models in a continuous speech recognizer. In: Proc. ICASSP 1994 (1994)
Novák, M., Hampl, R., Krbec, P., Bergl, V., Šedivý, J.: Two-Pass Search Strategy For Large List Recognition on Embedded Speech Recognition Platforms. In: ICASSP 2003 (2003)
Maison, B.: Automatic Baseform Generation from Acoustic Data. In: EuroSpeech 2003 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Beran, T. et al. (2004). Embedded ViaVoice. In: Sojka, P., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2004. Lecture Notes in Computer Science(), vol 3206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30120-2_34
Download citation
DOI: https://doi.org/10.1007/978-3-540-30120-2_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23049-6
Online ISBN: 978-3-540-30120-2
eBook Packages: Springer Book Archive