[Retracted] The Mongolian Vowel Acoustic Model Based on the Clustering Algorithm

Table 7

Recognition results of decision tree state before extraction.

Subjects	Sentence level recognition experimental results				Word level recognition experimental results
	% Correct	H	S	N	% Correct	ACC	H	D	S	I	N
Mongol 1	16.34	143	732	875	84.2	78.34	15088	353	2479	1050	17920
Mongol 2	25.14	178	530	708	91.33	84.42	10297	170	807	779	11274
Mongol-all	20.28	321	1262	1583	86.95	80.69	25385	523	3286	1829	29194
Dialogue 1	40.95	1757	2533	4290	83.24	72.96	16124	436	2811	1991	19371
Dialogue 2	43.55	1493	1936	3429	83.04	73.92	12399	292	2240	1362	14931
Dialogue 3	36.57	983	1705	2688	80.66	71.18	11298	278	2431	1328	14007
Dialogue-all	40.67	4233	6174	10407	82.43	72.74	39821	1006	7482	4681	48309