8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Large Vocabulary Continuous Speech Recognition Based on Cross-Morpheme Phonetic Information

In-Jeong Choi (1), Nam-Hoon Kim (1), Su Youn Yoon (2)

(1) Samsung Advanced Institution of Technology, Korea
(2) Seoul National University, Korea

In this paper, we present a novel method to regulate lexical connections among morpheme-based pronunciation lexicons for Korean large vocabulary continuous speech recognition (LVCSR) systems. A pronunciation dictionary plays an important role in subword-based LVCSR in that pronunciation variations such as coarticulation will deteriorate the performance of an LVCSR system if it is not well accounted for. In general, pronunciation variations are modeled by applying phonological variations with all possible phonemic contexts. In order to achieve high recognition performance, current speech recognition systems impose constraints among lexicons using both morphological and phonetic knowledge. This paper suggests a method both to refine pronunciation variations according to cross-morpheme phonetic information and to regulate the connections between pronunciation variants. This method effectively excludes improper connections between pronunciation lexicons, and thus the proposed method gave a 27% reduction in word error rate over the recognizer with conventional lexicons relatively.

Full Paper

Bibliographic reference.  Choi, In-Jeong / Kim, Nam-Hoon / Yoon, Su Youn (2004): "Large vocabulary continuous speech recognition based on cross-morpheme phonetic information", In INTERSPEECH-2004, 453-456.