No data available.
Please log in to see this content.
You have no subscription access to this content.
No metrics data to plot.
The attempt to load metrics for this article has failed.
The attempt to plot a graph for these metrics has failed.
The full text of this article is not currently available.
Model adaptation method for recognition of speech with missing frames
1. Bernard, A. , and Alwan, A. (2002). “ Low-bitrate distributed speech recognition for packet-based and wireless communication,” IEEE Trans. Speech and Audio Process. 10, 570–579.
3. Kim, W. , and Hansen, J. H. L. (2010). “ Missing-feature reconstruction by leveraging temporal spectral correlation for robust speech recognition in background noise conditions,” IEEE Trans. Audio, Speech, Lang. Process. 18, 2111–2120.
4. Lawrence, R. , and Rabiner, A. (1989). “ A tutorial on hidden Markov models and selected applications in speech recognition,” Proc. IEEE 77, 257–286.
6. Lee, L. M. (2013). “Variable frame rate speech decoding method,” http://sourceforge.net/projects/vfr-hmm/files/ (Last viewed Dec. 10, 2013).
8. Peinado, A. M. , Sánchez, V. , Pérez-Córdoba, J. L. , and de la Torre, Á. (2003). “ HMM-based channel error mitigation and its application to distributed speech recognition,” Speech Commun. 41, 549–561.
9. Siu, M. , and Chan, A. (2006). “ A robust Viterbi algorithm against impulse noise with application to speech recognition,” IEEE Trans. Audio, Speech, Lang. Process. 14, 2122–2133.
11. Tan, Z.-H. , Dalsgaard, P. , and Lindberg, B. (2007). “ Exploiting temporal correlation of speech for error robust and bandwidth flexible distributed speech recognition,” IEEE Trans. Audio, Speech, Lang. Process. 15, 1391–1403.
12. Young, S. , Evermann, G. , Gales, M. , Hain, T. , Kershaw, D. , Liu, X. , Moore, G. , Odell, J. , Ollason, D. , Povey, D. , Valtchev, V. , and Woodland, P. (2006). The HTK Book (for HTK version 3.4) (Department of Engineering at Cambridge University, Cambridge, UK).
Article metrics loading...
In distributed speech recognition (DSR), data packets may be lost over error prone channels. A commonly used approach to rectify this is to reconstruct a full frame rate data sequence for recognition using linear interpolation. In this study, an error-concealment decoding method that dynamically adapts the transition probabilities of hidden Markov models to match the frame loss observation sequence is proposed. Experimental results show that a DSR system using the proposed method can achieve the same level of accuracy as a data reconstruction method, is more robust against heavy frame loss, and significantly reduces the computation time.
Full text loading...
Most read this month