대한음성학회:학술대회논문집 (Proceedings of the KSPS conference)
- 대한음성학회 2006년도 추계학술대회 발표논문집
- /
- Pages.80-83
- /
- 2006
음소변동규칙의 적합도 조정을 통한 연속음성인식 성능향상
Improving the Performance of the Continuous Speech Recognition by Estimating Likelihoods of the Phonetic Rules
-
Na, Min-Soo
(Interdisciplinary Program in Cognitive Science, Seoul National University) ;
-
Chung, Min-Hwa
(Department of Linguistics, Seoul National University)
- 발행 : 2006.11.17
초록
The purpose of this paper is to build a pronunciation lexicon with estimated likelihoods of the phonetic rules based on the phonetic realizations and therefore to improve the performance of CSR using the dictionary. In the baseline system, the phonetic rules and their application probabilities are defined with the knowledge of Korean phonology and experimental tuning. The advantage of this approach is to implement the phonetic rules easily and to get stable results on general domains. However, a possible drawback of this method is that it is hard to reflect characteristics of the phonetic realizations on a specific domain. In order to make the system reflect phonetic realizations, the likelihood of phonetic rules is reestimated based on the statistics of the realized phonemes using a forced-alignment method. In our experiment, we generates new lexica which include pronunciation variants created by reestimated phonetic rules and its performance is tested with 12 Gaussian mixture HMMs and back-off bigrams. The proposed method reduced the WER by 0.42%.
키워드