1887
banner image
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.
oa
Model adaptation method for recognition of speech with missing frames
Rent:
Rent this article for
Access full text Article
/content/asa/journal/jasa/135/3/10.1121/1.4865264
1.
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, 570579.
http://dx.doi.org/10.1109/TSA.2002.808141
2.
2. Gilbert, N. (1960). “ Capacity of a burst-noise channel,” Bell Syst. Tech. J. 39, 12531265.
http://dx.doi.org/10.1002/j.1538-7305.1960.tb03959.x
3.
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, 21112120.
http://dx.doi.org/10.1109/TASL.2010.2041698
4.
4. Lawrence, R. , and Rabiner, A. (1989). “ A tutorial on hidden Markov models and selected applications in speech recognition,” Proc. IEEE 77, 257286.
http://dx.doi.org/10.1109/5.18626
5.
5. Lee, L.-M. (2010). “ Adaptation of hidden Markov models for half frame rate observations,” Electron. Lett. 46, 723724.
http://dx.doi.org/10.1049/el.2010.0942
6.
6. Lee, L. M. (2013). “Variable frame rate speech decoding method,” http://sourceforge.net/projects/vfr-hmm/files/ (Last viewed Dec. 10, 2013).
7.
7. Lee, L. M. , and Jean, F. R. (2013). “ Adaptation of hidden Markov models for recognizing speech of reduced frame rate,” IEEE Trans. Cybern. 43, 21142121.
http://dx.doi.org/10.1109/TCYB.2013.2240450
8.
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, 549561.
http://dx.doi.org/10.1016/S0167-6393(03)00048-7
9.
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, 21222133.
http://dx.doi.org/10.1109/TASL.2006.872592
10.
10. Tan, Z.-H. , Dalsgaard, P. , and Lindberg, B. (2005). “ Automatic speech recognition over error-prone wireless networks,” Speech Commun. 47, 220242.
http://dx.doi.org/10.1016/j.specom.2005.05.007
11.
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, 13911403.
http://dx.doi.org/10.1109/TASL.2006.889799
12.
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).
http://aip.metastore.ingenta.com/content/asa/journal/jasa/135/3/10.1121/1.4865264
Loading
/content/asa/journal/jasa/135/3/10.1121/1.4865264
Loading

Data & Media loading...

Loading

Article metrics loading...

/content/asa/journal/jasa/135/3/10.1121/1.4865264
2014-02-21
2014-08-27

Abstract

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.

Loading

Full text loading...

/deliver/fulltext/asa/journal/jasa/135/3/1.4865264.html;jsessionid=1won9tq03y6ow.x-aip-live-03?itemId=/content/asa/journal/jasa/135/3/10.1121/1.4865264&mimeType=html&fmt=ahah&containerItemId=content/asa/journal/jasa
true
true
This is a required field
Please enter a valid email address
This feature is disabled while Scitation upgrades its access control system.
This feature is disabled while Scitation upgrades its access control system.
752b84549af89a08dbdd7fdb8b9568b5 journal.articlezxybnytfddd
Scitation: Model adaptation method for recognition of speech with missing frames
http://aip.metastore.ingenta.com/content/asa/journal/jasa/135/3/10.1121/1.4865264
10.1121/1.4865264
SEARCH_EXPAND_ITEM