TY - JOUR
T1 - Expanding vocabulary for recognizing user's abbreviations of proper nouns without increasing ASR error rates in spoken dialogue systems
AU - Katsumaru, Masaki
AU - Komatani, Kazunori
AU - Ogata, Tetsuya
AU - Okuno, Hiroshi G.
N1 - Funding Information:
Research sponsored by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory (ORNL), managed by UT-Battelle, LLC for the U. S. Department of Energy under Contract No. DE-AC05-00OR22725.
Funding Information:
★ Research sponsored by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory (ORNL), managed by UT-Battelle, LLC for the U. S. Department of Energy under Contract No. DE-AC05-00OR22725. 1 http://www.iter.org/
PY - 2008
Y1 - 2008
N2 - Users often abbreviate long words when using spoken dialogue systems, which results in automatic speech recognition (ASR) errors. We define abbreviated words as sub-words of the original word, and add them into an ASR dictionary. The first problem is that proper nouns cannot be correctly segmented by general morphological analyzers, although long and compounded words need to be segmented in agglutinative languages such as Japanese. The second is that, as vocabulary increases, adding many abbreviated words degrades the ASR accuracy. We develop two methods, (1) to segment words by using conjunction probabilities between characters, and (2) to manipulate occurrence probabilities of generated abbreviated words on the basis of the phonological similarities between abbreviated and original words. By our method, the ASR accuracy is improved by 24.2 points for utterances containing abbreviated words, and degraded by only a 0.1 point for those containing original words.
AB - Users often abbreviate long words when using spoken dialogue systems, which results in automatic speech recognition (ASR) errors. We define abbreviated words as sub-words of the original word, and add them into an ASR dictionary. The first problem is that proper nouns cannot be correctly segmented by general morphological analyzers, although long and compounded words need to be segmented in agglutinative languages such as Japanese. The second is that, as vocabulary increases, adding many abbreviated words degrades the ASR accuracy. We develop two methods, (1) to segment words by using conjunction probabilities between characters, and (2) to manipulate occurrence probabilities of generated abbreviated words on the basis of the phonological similarities between abbreviated and original words. By our method, the ASR accuracy is improved by 24.2 points for utterances containing abbreviated words, and degraded by only a 0.1 point for those containing original words.
KW - Abbreviated words
KW - Proper nouns
KW - Spoken dialogue systems
KW - Vocabulary expansion
UR - http://www.scopus.com/inward/record.url?scp=84867221569&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867221569&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:84867221569
SP - 187
EP - 190
JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
SN - 2308-457X
T2 - INTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association
Y2 - 22 September 2008 through 26 September 2008
ER -