tailieunhanh - Speech recognition using neural networks - Chapter 5

Databases Chúng tôi thực hiện các thí nghiệm của chúng tôi về NN-HMM lai bằng cách sử dụng ba cơ sở dữ liệu khác nhau: máy bay ATR của cơ sở dữ liệu của từ Nhật Bản bị cô lập, Hội nghị đăng ký CMU cơ sở dữ liệu, và cơ sở dữ liệu Quản lý tài nguyên DARPA. Trong chương này chúng tôi sẽ mô tả ngắn gọn của các cơ sở dữ liệu. | 5. Databases We performed our experiments on NN-HMM hybrids using three different databases ATR s database of isolated Japanese words the CMU Conference Registration database and the DARPA Resource Management database. In this chapter we will briefly describe each of these databases. . Japanese Isolated Words Our very first experiments were performed using a database of 5240 isolated Japanese words Sagisaka et al 1987 provided by ATR Interpreting Telephony Research Laboratory in Japan with whom we were collaborating. This database includes recordings of all 5240 words by several different native Japanese speakers all of whom are professional announcers but our experiments used the data from only one male speaker MAU . Each isolated word was recorded in a soundproof booth and digitized at a 12 kHz sampling rate. A Hamming window and an FFT were applied to the input data to produce 16 melscale spectral coefficients every 10 msec. Because our computational resources were limited at the time we chose not to use all 5240 words in this database instead we extracted two subsets based on a limited number of phonemes Subset 1 299 words representing 234 unique words due to the presence of homophones comprised of only the 7 phonemes a i u o k s sh plus an eighth phoneme for silence . From these 299 words we trained on 229 words and tested on the remaining 70 words of which 50 were homophones of training samples and 20 were novel words . Table shows this vocabulary. Subset 2 1078 words representing 924 unique words comprised of only the 13 phonemes a i u e o k r s t kk sh ts tt plus a 14th phoneme for silence . From these 1078 words we trained on 900 words and tested on 178 words of which 118 were homophones of training samples and 60 were novel words . Using homophones in the testing set allowed us to test generalization to new samples of known words while the unique words allowed us to test generalization to novel words . vocabulary independence . 73 74 5. .