Landmark-Guided Segmental Speech Decoding for Continuous Mandarin Speech Recognition

Hao Chao and Cheng Song
Volume: 12, No: 3, Page: 410 ~ 421, Year: 2016
10.3745/JIPS.03.0052
Keywords: Decoding, Landmark, Mandarin, Speech Recognition, Segment Model
Full Text:

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.

Article Statistics
Multiple requests among the same broswer session are counted as one view (or download).
If you mouse over a chart, a box will show the data point's value.


Cite this article
IEEE Style
Hao Chao and Cheng 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, "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.