Research ArticleOpen accessPhrase in the titleAcoustic Model Adaptation for Indonesian Language Utterance Training SystemLinda Indrayanti, Yoshifumi Chisaki, Tsuyoshi UsagawaProblem statement: In order to build an utterance training system for Indonesian language, a speech recognition system designed for Indonesian is necessary. However, the system hardly works well due to the pronunciation variants of non-native utterances may lead to substitution/deletion error. This research investigated the pronunciation variant and proposes acoustic model adaptation to improve performance of the system. Approach: The … …Journal of Computer Science, Vol. 6, Issue 11 · 23 Oct 2010 · 7,168 accessesView PDFCite
Research ArticleOpen accessIn the abstractCorpus-Based Analysis on Cross-Domain Experiments in Classification-and-Ranking GenerationAida Mustapha, Md. Nasir Sulaiman, Ramlan Mahmod, Mohd. Hasan SelamatProblem statement: Overgeneration-and-ranking architecture works well in written language where sentence is the basic unit. However, in spoken language where utterance is the basic unit, the disadvantage becomes critical as spoken language also render intentions, hence short strings may be of equivalent impact. Approach: In classification-and-ranking, response was deliberately chosen from dialogue corpus rather than wholly generated, such that it … …Journal of Computer Science, Vol. 6, Issue 11 · 23 Oct 2010 · 7,097 accessesView PDFCite