Landmark-Guided Segmental Speech Decoding for Continuous Mandarin Speech Recognition


Hao Chao, Cheng Song, Journal of Information Processing Systems Vol. 12, No. 3, pp. 410-421, Sep. 2016  

10.3745/JIPS.03.0052
Keywords: Decoding, Landmark, Mandarin, speech recognition, Segment Model
Fulltext:

Abstract

In this paper, we propose a framework that attempts to incorporate landmarks into a segment-based Mandarin speech recognition system. In this method, landmarks provide boundary information and phonetic class information, and the information is used to direct the decoding process. To prove the validity of this method, two kinds of landmarks that can be reliably detected are used to direct the decoding process of a segment model (SM) based Mandarin LVCSR (large vocabulary continuous speech recognition) system. The results of our experiment show that about 30% decoding time can be saved without an obvious decrease in recognition accuracy. Thus, the potential of our method is demonstrated.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.




Cite this article
[APA Style]
Chao, H. & Song, C. (2016). Landmark-Guided Segmental Speech Decoding for Continuous Mandarin Speech Recognition. Journal of Information Processing Systems, 12(3), 410-421. DOI: 10.3745/JIPS.03.0052.

[IEEE Style]
H. Chao and C. Song, "Landmark-Guided Segmental Speech Decoding for Continuous Mandarin Speech Recognition," Journal of Information Processing Systems, vol. 12, no. 3, pp. 410-421, 2016. DOI: 10.3745/JIPS.03.0052.

[ACM Style]
Hao Chao and Cheng Song. 2016. Landmark-Guided Segmental Speech Decoding for Continuous Mandarin Speech Recognition. Journal of Information Processing Systems, 12, 3, (2016), 410-421. DOI: 10.3745/JIPS.03.0052.