Title :
Improvement of speech processing using fuzzy logic approach
Author_Institution :
Dept. of Microelectron. and Comput. Sci., Tech. Univ. Lodz, Poland
Abstract :
Two problems are discussed. The first is how to improve the signal-to-noise ratio (SNR) owing to the digital structure of the computer voice using a fuzzy logic approach. The second one is how to efficiently recognize a whole word from a given vocabulary, taking into account tree structures as a background of decision algorithm. Since the spoken language can very often be ambiguous, then it was useful to include a fuzzy approach to obtain more effective methods of speech processing
Keywords :
fuzzy logic; knowledge based systems; speech recognition; speech synthesis; tree data structures; word processing; SNR; computer voice; decision algorithm; digital structure; fuzzy approach; fuzzy logic approach; signal-to-noise ratio; speech processing; spoken language; tree structures; word recognition; Acoustic noise; Finite impulse response filter; Fuzzy logic; Noise shaping; Quantization; Signal processing; Signal to noise ratio; Speech processing; Speech synthesis; Vocabulary;
Conference_Titel :
IFSA World Congress and 20th NAFIPS International Conference, 2001. Joint 9th
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-7078-3
DOI :
10.1109/NAFIPS.2001.944692
