Candidate Generation for ASR Output Error Correction Using a Context-Dependent Syllable Cluster-Based Confusion Matrix

Error correction techniques have been proposed in the applications of language learning and spoken dialogue systems for spoken language understanding. These techniques include two consecutive stages: the generation of correction candidates and the selection of correction candidates. In this study, a Context-Dependent Syllable Cluster (CD-SC)-based Confusion Matrix is proposed for the generation of correction candidates. A Contextual Fitness Score, measuring the sequential relationship to the neighbors of the candidate, is proposed for corrected syllable sequence selection. Finally, the n-gram language model is used to determine the final word sequence output. Experiments show that the proposed method improved from 0.742 to 0.771 in terms of BLEU score as compared to the conventional speech recognition mechanism.

[1]  Chung-Hsien Wu,et al.  Prosodic word-based error correction in speech recognition using prosodic word expansion and contextual information , 2010, INTERSPEECH.

[2]  Chung-Hsien Wu,et al.  Sentence Correction Incorporating Relative Position and Parse Template Language Models , 2010, IEEE Transactions on Audio, Speech, and Language Processing.

[3]  Ramón López-Cózar,et al.  ASR post-correction for spoken dialogue systems based on semantic, syntactic, lexical and contextual information , 2008, Speech Commun..

[4]  Julia Hirschberg,et al.  Error handling in spoken dialogue systems , 2005, Speech Commun..

[5]  Lei Zhang,et al.  Automatic Detecting/Correcting Errors in Chinese Text by an Approximate Word-Matching Algorithm , 2000, ACL.

[6]  Chung-Hsien Wu,et al.  Word Order Correction for Language Transfer Using Relative Position Language Modeling , 2008, 2008 6th International Symposium on Chinese Spoken Language Processing.

[7]  Michael Gamon,et al.  Correcting ESL Errors Using Phrasal SMT Techniques , 2006, ACL.

[8]  Chung-Hsien Wu,et al.  Recovery from false rejection using statistical partial pattern trees for sentence verification , 2004, Speech Commun..

[9]  Stephanie Seneff,et al.  Automatic grammar correction for second-language learners , 2006, INTERSPEECH.

[10]  Yih-Ru Wang.  A New Similarity Measure Between HMMS , 2008, 2008 6th International Symposium on Chinese Spoken Language Processing.

[11]  Teruko Mitamura,et al.  Correction Grammars for Error Handling in a Speech Dialog System , 2004, HLT-NAACL.