Identifying method capable of identifying all languages without using samples

摘要: PROBLEM TO BE SOLVED: To provide an identification method correctly identifying all language sentences by improving a feature of continuous sound, and thereby, languages such as Taiwan-Chinese, English, Japanese, German, French, Korean, Russian, Cantonese Taiwanese, without using samples. SOLUTION: The sound (word) includes one or more single short duration sounds, the is extracted from unknown languages. displayed matrix value, dispersed to 144-dimensional space, known simulated calculated around sound. including 12 elastic frames with same length, filters overlapping, converted wave 12×12 various lengths, compared identified Bayes' method. COPYRIGHT: (C)2011,JPO&INPIT