TY - GEN
T1 - Non-native English speakers' speech correction, based on domain focused document
AU - Radzikowski, Kacper
AU - Wang, Le
AU - Yoshie, Osamu
PY - 2016/11/28
Y1 - 2016/11/28
N2 - With the increase in exchange programs, many international students worldwide can face communication problems. Dur-ing lectures, usually English language is used for the commu-nication between students and teachers. However both sides, not necessarily being native speakers of English, may misun-derstand each other. In this paper we propose a method for correction of non-native English speakers' speech, based on the domain focused electronic document. The method relies on the results of speech recognition (SR) software, and uses them altogether with the document. Our approach consists of three steps. Firstly, document analysis in the preprocess-ing phase. Secondly, finding the document part correspond-ing to sentence from SR software, realised using the Hidden Markov Model (HMM) based method. Finally, the correc-tion by calculating the score for each of candidate sentences, based on the result of SR software. The probability score combines keywords comparison, BM25F method and HMM based method scores. Highest score candidate is chosen as replacement.
AB - With the increase in exchange programs, many international students worldwide can face communication problems. Dur-ing lectures, usually English language is used for the commu-nication between students and teachers. However both sides, not necessarily being native speakers of English, may misun-derstand each other. In this paper we propose a method for correction of non-native English speakers' speech, based on the domain focused electronic document. The method relies on the results of speech recognition (SR) software, and uses them altogether with the document. Our approach consists of three steps. Firstly, document analysis in the preprocess-ing phase. Secondly, finding the document part correspond-ing to sentence from SR software, realised using the Hidden Markov Model (HMM) based method. Finally, the correc-tion by calculating the score for each of candidate sentences, based on the result of SR software. The probability score combines keywords comparison, BM25F method and HMM based method scores. Highest score candidate is chosen as replacement.
KW - BM25F
KW - Domain document
KW - HMM
KW - Sentence cor-rection
KW - Speech recognition correction
UR - http://www.scopus.com/inward/record.url?scp=85014968612&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85014968612&partnerID=8YFLogxK
U2 - 10.1145/3011141.3011169
DO - 10.1145/3011141.3011169
M3 - Conference contribution
AN - SCOPUS:85014968612
T3 - ACM International Conference Proceeding Series
SP - 276
EP - 281
BT - 18th International Conference on Information Integration and Web-Based Applications and Services, iiWAS 2016 - Proceedings
A2 - Indrawan-Santiago, Maria
A2 - Anderst-Kotsis, Gabriele
A2 - Steinbauer, Matthias
A2 - Khalil, Ismail
PB - Association for Computing Machinery
T2 - 18th International Conference on Information Integration and Web-Based Applications and Services, iiWAS 2016
Y2 - 28 November 2016 through 30 November 2016
ER -