Special key-value store - header only database for n-gram models

• Autorzy: Skurzok D. , Ziółko B.
• Języki publikacji: EN

Abstrakty

EN

Aspects of applying databases in speech recognition are presented. An example of a dictionary and an n-gram model of the AGH automatic speech recognition system SARMATA are depicted. An advantage of our own key-value store implementation HODB, comparing to SQLite and Berkeley DB in time efficiency aspects is shown.

Słowa kluczowe

EN

n-gram models; databases; hash functions; time efficiency

PL

model n-gramowy; bazy danych; funkcja Hash; wydajność czasu

• Wydawca: Wydawnictwo Politechniki Łódzkiej
• Czasopismo: Journal of Applied Computer Science
• Rocznik: 2012
• Tom: Vol. 20, nr 2
• Strony: 119--129
• Opis fizyczny: Bibliogr. 10 poz.

Twórcy

autor

Skurzok D.

autor

Ziółko B.

• AGH University of Science and Technology, Department of Electronics, al. Mickiewicza 30, Kraków, Poland,

Bibliografia

• [1] Ziółko, M., Gałka, J., Ziółko, B., Jadczyk, T., Skurzok, D., and Ma ?sior, M., Automatic Speech Recognition System Dedicated for Polish, Proceedings of Interspeech, Florence, 2011.
• [2] Ziółko, B. and Skurzok, D., N-grams model for Polish, Speech and Language Technologies, Book 2, InTech Publisher, 2011, pp. 107–127.
• [3] Ziółko, B., Skurzok, D., and Michalska, M., Polish n-grams and their correction process, Proceedings of The 4th International Conference on Multimedia and Ubiquitous Engineering (MUE 2010), Cebu, Philipines, 2010.
• [4] Ney, H., Essen, U., and Kneser, R., On structuring probabilistic dependencies in stochastic language modelling, Computer Speech and Language, Vol. 8, 1994, pp. 1–38.
• [5] Kneser, R. and Ney, H., Improved backing-o for m-gram language modelling, Proceedings of International Conference on Acoustics, Speech, and Signal Processing, ICASSP, 1995, pp. 181–184.
• [6] Hirsimaki, T., Pylkkonen, J., and Kurimo, M., Importance of high-order ngram models in morph-based speech recognition, IEEE Transactions on Audio, Speech and Language Processing, Vol. 17(4), 2009, pp. 724–32.
• [7] Khudanpur, S. and Wu, J., A maximum entropy language model integrating n-grams and topic dependencies for conversational speech recognition, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Phoenix, AZ, 1999.
• [8] Skurzok, D., Ziółko, B., Pohl, A., Jadczyk, T., and Ma ?sior, M., Comparative study of SQLite and Berkeley DB implementations of n-gram model of Polish language, Studia Informatica, Vol. 33, No. 2B, 2012, pp. 153–162.
• [9] Whittaker, E. and Woodland, P., Language modelling for Russian and English using words and classes, Computer Speech and Language, Vol. 17, 2003, pp. 87–104.
• [10] Noll, L. C., Fowler / Noll / Vo (FNV) hash, 2004.